Dissertations / Theses on the topic 'Multi-cloud architecture'

Le Cloud Computing est un nouveau modèle économique hébergeant les applications de la technologie de l’information. Le passage au Cloud devient un enjeu important des entreprises pour des raisons économiques. La nature dynamique et la complexité croissante des architectures de Cloud impliquent plusieurs défis de gestion. Dans ce travail, nous nous intéressons à la gestion des contrats SLA. Vu le manque de standardisation, chaque fournisseur de service décrit les contrats SLA avec son propre langage, ce qui laisse l'utilisateur perplexe concernant le choix de son fournisseur de services. Dans ce travail, nous proposons une architecture de Cloud Broker permettant d’établir et de négocier les contrats SLA entre les fournisseurs et les consommateurs du Cloud. L’objectif de cette architecture est d’aider l’utilisateur à trouver le meilleur fournisseur en utilisant une méthode multi-critère. Cette méthode considère chaque critère comme une fonction d’utilité à intégrer dans une super-fonction d’utilité. Nous proposons d’illustrer chaque fonction d’utilité par une courbe spécifique à lui représentant bien le critère de choix. Nous essayons de cerner la plupart des critères qui contribuent dans le choix du meilleurs service et de les classer en critères fonctionnels et critères non fonctionnels. Les contrats SLA établit par notre broker sont formalisés sous forme d’ontologies qui permettent de masquer l'hétérogénéité et d’assurer l'interopérabilité entre les acteurs du Cloud. En outre, l’utilisation des règles d'inférence nous a permis de détecter les violations dans le contrat SLA établit et de garantir ainsi le respect de la satisfaction client dans le temps<br>Cloud Computing is a dynamic new technology that has huge potentials in enterprises and markets. The dynamicity and the increasing complexity of Cloud architectures involve several management challenges. In this work, we are interested in Service Level Agreement (SLA) management. Actually, there is no standard to express Cloud SLA, so, providers describe their SLAs in different manner and different languages, which leaves the user puzzled about the choice of its Cloud provider. To overcome these problems, we introduce a Cloud Broker Architecture managing the SLA between providers and consumers. It aims to assist users in establishing and negotiating SLA contracts and to help them in finding the best provider that satisfies their service level expectations. Our broker SLA contracts are formalized as OWL ontologies as they allow hiding the heterogeneity in the distributed Cloud environment and enabling interoperability between Cloud actors. Besides, by combining our ontology with our proposed inference rules, we contribute to detect violations in the SLA contract assuring thereby the sustainability of the user satisfaction. Based on the requirements specified in the SLA contract, our Cloud Broker assists users in selecting the right provider using a multi attribute utility theory method. This method is based on utility functions representing the user satisfaction degree. To obtain accurate results, we have modelled both functional and non functional attributes utilities. We have used personalized utilities for each criterion under negotiation so that our cloud broker satisfies the best consumer requirements from functional and non functional point of view

Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, System Design and Management Program, 2017.<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 97-101).<br>Cloud computing is widely adopted in industry sectors of finance, energy and transportation. Public cloud service providers are able to consistently deliver solutions that meet demanding needs of security, availability, scalability of mission-critical applications. The low cost of compute and storage, combined with expanding coverage of high speed cellular networks, have enabled a wide expansion of telemetry services and consumer applications in automobiles, but safety applications are not leveraging these benefits. The majority of traffic fatalities happens in high-speed multi-vehicle crashes. Causal analysis of multi-vehicle crashes reveal process model inconsistencies that lead the drivers to make wrong assumptions about vehicle capabilities and lead-vehicle separation distances during adverse road conditions. The Spot Weather Impact Warning (SWIW) is a connected vehicle application concept proposed by the US Department of Transportation (DOT) that alerts drivers to unsafe conditions at specific points on the downstream roadway as a result of weather-related impacts. The application is designed to warn drivers about inclement weather conditions that may impact travel conditions using real-time weather information that is collected from roadway infrastructure and vehicle based probe data. The information is processed to determine the nature of the alert or warning to be delivered and then communicated to connected vehicles. The effectiveness of SWIW connected vehicle application depends on the probe coverage and the speed that probe data can be collected, analyzed, and broadcasted to relevant vehicles and roadway signage. To reach a sufficient coverage without high investment in new infrastructure, SWIW applications can be architected to use existing mobile operators and cloud service providers. A deeper Systems Theoretic Process Analysis of the application reveals that varying levels of vehicle-to-cloud communication performance may lead to process model inconsistencies for drivers, resulting in unsafe control actions from driver that ignore warnings and lead to accidents. To validate the vehicle to cloud communication performance, the SWIW application prototype is built using existing cloud service and vehicle platform. The performance of the application is validated across all tier-one cloud and mobile service providers in 10,000 miles of US roadways. The test results reveal the presence of low latency corridors in the US that may support the initial deployment of low latency solution. String stability model showed that significant reduction in probability of accidents is possible even at low penetration rates of the solution. The solution's operational cost analysis also concludes that a limited deployment on commercial vehicles has the potential of saving high value corridors such as the 402-mile Wyoming I-80 corridor as much as $1.5 million per day of socio-economic losses in accidents with an operational cost of $763 per day. This thesis concludes that connected vehicle programs that are addressing multi-vehicle accidents in low latency corridors should consider commercial fleet deployments that use mobile and public cloud service providers to quickly reach minimal penetration rate and socio-economic benefits.<br>by Ricardo DeMatos.<br>S.M. in Engineering and Management

Le Cloud Computing est un nouveau modèle économique hébergeant les applications de la technologie de l’information. Le passage au Cloud devient un enjeu important des entreprises pour des raisons économiques. La nature dynamique et la complexité croissante des architectures de Cloud impliquent plusieurs défis de gestion. Dans ce travail, nous nous intéressons à la gestion des contrats SLA. Vu le manque de standardisation, chaque fournisseur de service décrit les contrats SLA avec son propre langage, ce qui laisse l'utilisateur perplexe concernant le choix de son fournisseur de services. Dans ce travail, nous proposons une architecture de Cloud Broker permettant d’établir et de négocier les contrats SLA entre les fournisseurs et les consommateurs du Cloud. L’objectif de cette architecture est d’aider l’utilisateur à trouver le meilleur fournisseur en utilisant une méthode multi-critère. Cette méthode considère chaque critère comme une fonction d’utilité à intégrer dans une super-fonction d’utilité. Nous proposons d’illustrer chaque fonction d’utilité par une courbe spécifique à lui représentant bien le critère de choix. Nous essayons de cerner la plupart des critères qui contribuent dans le choix du meilleurs service et de les classer en critères fonctionnels et critères non fonctionnels. Les contrats SLA établit par notre broker sont formalisés sous forme d’ontologies qui permettent de masquer l'hétérogénéité et d’assurer l'interopérabilité entre les acteurs du Cloud. En outre, l’utilisation des règles d'inférence nous a permis de détecter les violations dans le contrat SLA établit et de garantir ainsi le respect de la satisfaction client dans le temps<br>Cloud Computing is a dynamic new technology that has huge potentials in enterprises and markets. The dynamicity and the increasing complexity of Cloud architectures involve several management challenges. In this work, we are interested in Service Level Agreement (SLA) management. Actually, there is no standard to express Cloud SLA, so, providers describe their SLAs in different manner and different languages, which leaves the user puzzled about the choice of its Cloud provider. To overcome these problems, we introduce a Cloud Broker Architecture managing the SLA between providers and consumers. It aims to assist users in establishing and negotiating SLA contracts and to help them in finding the best provider that satisfies their service level expectations. Our broker SLA contracts are formalized as OWL ontologies as they allow hiding the heterogeneity in the distributed Cloud environment and enabling interoperability between Cloud actors. Besides, by combining our ontology with our proposed inference rules, we contribute to detect violations in the SLA contract assuring thereby the sustainability of the user satisfaction. Based on the requirements specified in the SLA contract, our Cloud Broker assists users in selecting the right provider using a multi attribute utility theory method. This method is based on utility functions representing the user satisfaction degree. To obtain accurate results, we have modelled both functional and non functional attributes utilities. We have used personalized utilities for each criterion under negotiation so that our cloud broker satisfies the best consumer requirements from functional and non functional point of view

Tese (doutorado)—Universidade de Brasília, Instituto de Ciências Exatas, Departamento de Ciência da Computação, 2014.<br>Submitted by Ana Cristina Barbosa da Silva (annabds@hotmail.com) on 2015-05-25T14:38:06Z No. of bitstreams: 1 2014_AlessandroFerreiraLeite.pdf: 9950238 bytes, checksum: 5899f0fba30e3075ce700c4440d984f9 (MD5)<br>Approved for entry into archive by Guimaraes Jacqueline(jacqueline.guimaraes@bce.unb.br) on 2015-05-25T15:49:14Z (GMT) No. of bitstreams: 1 2014_AlessandroFerreiraLeite.pdf: 9950238 bytes, checksum: 5899f0fba30e3075ce700c4440d984f9 (MD5)<br>Made available in DSpace on 2015-05-25T15:49:14Z (GMT). No. of bitstreams: 1 2014_AlessandroFerreiraLeite.pdf: 9950238 bytes, checksum: 5899f0fba30e3075ce700c4440d984f9 (MD5)<br>A computação em nuvem tem sido considerada como uma opção para executar aplicações de alto desempenho. Entretanto, enquanto as plataformas de alto desempenho tradicionais como grid e supercomputadores oferecem um ambiente estável quanto à falha, desempenho e número de recursos, a computação em nuvem oferece recursos sob demanda, geralmente com desempenho imprevisível à baixo custo financeiro. Além disso, em ambiente de nuvem, as falhas fazem parte da sua normal operação. No entanto, as nuvens podem ser combinadas, criando uma federação, para superar os limites de uma nuvem muitas vezes com um baixo custo para os usuários. A federação de nuvens pode ajudar tanto os provedores quanto os usuários das nuvens a atingirem diferentes objetivos tais como: reduzir o tempo de execução de uma aplicação, reduzir o custo financeiro, aumentar a disponibilidade do ambiente, reduzir o consumo de energia, entre outros. Por isso, a federação de nuvens pode ser uma solução elegante para evitar o sub-provisionamento de recursos ajudando os provedores a reduzirem os custos operacionais e a reduzir o número de recursos ativos, que outrora ficariam ociosos consumindo energia, por exemplo. No entanto, a federação de nuvens aumenta as opções de recursos disponíveis para os usuários, requerendo, em muito dos casos, conhecimento em administração de sistemas ou em computação em nuvem, bem como um tempo considerável para aprender sobre as opções disponíveis. Neste contexto, surgem algumas questões, tais como: (a) qual dentre os recursos disponíveis é apropriado para uma determinada aplicação? (b) como os usuários podem executar suas aplicações na nuvem e obter um desempenho e um custo financeiro aceitável, sem ter que modificá-las para atender as restrições do ambiente de nuvem? (c) como os usuários não especialistas em nuvem podem maximizar o uso da nuvem, sem ficar dependente de um provedor? (d) como os provedores podem utilizar a federação para reduzir o consumo de energia dos datacenters e ao mesmo tempo atender os acordos de níveis de serviços? A partir destas questões, este trabalho apresenta uma solução para consolidação de aplicações em nuvem federalizadas considerando os acordos de serviços. Nossa solução utiliza um sistema multi-agente para negociar a migração das máquinas virtuais entres as nuvens. Simulações mostram que nossa abordagem pode reduzir em até 46% o consumo de energia e atender os requisitos de qualidade. Nós também desenvolvemos e avaliamos uma solução para executar uma aplicação de bioinformática em nuvens federalizadas, a custo zero. Nesse caso, utilizando a federação, conseguimos diminuir o tempo de execução da aplicação em 22,55%, considerando o seu tempo de execução na melhor nuvem. Além disso, este trabalho apresenta uma arquitetura chamada Excalibur, que possibilita escalar a execução de aplicações comuns em nuvem. Excalibur conseguiu escalar automaticamente a execução de um conjunto de aplicações de bioinformática em até 11 máquinas virtuais, reduzindo o tempo de execução em 63% e o custo financeiro em 84% quando comparado com uma configuração definida pelos usuários. Por fim, este trabalho apresenta um método baseado em linha de produto de software para lidar com as variabilidades dos serviços oferecidos por nuvens de infraestrutura (IaaS), e um sistema que utiliza deste processo para configurar o ambiente e para lidar com falhas de forma automática. O nosso método utiliza modelo de feature estendido com atributos para descrever os recursos e para selecioná-los com base nos objetivos dos usuários. Experimentos realizados com dois provedores diferentes mostraram que utilizando o nosso processo, os usuários podem executar as suas aplicações em um ambiente de nuvem federalizada, sem conhecer as variabilidades e limitações das nuvens. _______________________________________________________________________________________ ABSTRACT<br>Cloud computing has been seen as an option to execute high performance computing (HPC) applications. While traditional HPC platforms such as grid and supercomputers offer a stable environment in terms of failures, performance, and number of resources, cloud computing offers on-demand resources generally with unpredictable performance at low financial cost. Furthermore, in cloud environment, failures are part of its normal operation. To overcome the limits of a single cloud, clouds can be combined, forming a cloud federation often with minimal additional costs for the users. A cloud federation can help both cloud providers and cloud users to achieve their goals such as to reduce the execution time, to achieve minimum cost, to increase availability, to reduce power consumption, among others. Hence, cloud federation can be an elegant solution to avoid over provisioning, thus reducing the operational costs in an average load situation, and removing resources that would otherwise remain idle and wasting power consumption, for instance. However, cloud federation increases the range of resources available for the users. As a result, cloud or system administration skills may be demanded from the users, as well as a considerable time to learn about the available options. In this context, some questions arise such as: (a) which cloud resource is appropriate for a given application? (b) how can the users execute their HPC applications with acceptable performance and financial costs, without needing to re-engineer the applications to fit clouds’ constraints? (c) how can non-cloud specialists maximize the features of the clouds, without being tied to a cloud provider? and (d) how can the cloud providers use the federation to reduce power consumption of the clouds, while still being able to give service-level agreement (SLA) guarantees to the users? Motivated by these questions, this thesis presents a SLA-aware application consolidation solution for cloud federation. Using a multi-agent system (MAS) to negotiate virtual machine (VM) migrations between the clouds, simulation results show that our approach could reduce up to 46% of the power consumption, while trying to meet performance requirements. Using the federation, we developed and evaluated an approach to execute a huge bioinformatics application at zero-cost. Moreover, we could decrease the execution time in 22.55% over the best single cloud execution. In addition, this thesis presents a cloud architecture called Excalibur to auto-scale cloud-unaware application. Executing a genomics workflow, Excalibur could seamlessly scale the applications up to 11 virtual machines, reducing the execution time by 63% and the cost by 84% when compared to a user’s configuration. Finally, this thesis presents a software product line engineering (SPLE) method to handle the commonality and variability of infrastructure-as-a-service (IaaS) clouds, and an autonomic multi-cloud architecture that uses this method to configure and to deal with failures autonomously. The SPLE method uses extended feature model (EFM) with attributes to describe the resources and to select them based on the users’ objectives. Experiments realized with two different cloud providers show that using the proposed method, the users could execute their application on a federated cloud environment, without needing to know the variability and constraints of the clouds. _______________________________________________________________________________________ RÉSUMÉ<br>Le cloud computing a été considéré comme une option pour exécuter des applications de calcul haute performance (HPC). Bien que les plateformes traditionnelles de calcul haute performance telles que les grilles et les supercalculateurs offrent un environnement stable du point de vue des défaillances, des performances, et de la taille des ressources, le cloud computing offre des ressources à la demande, généralement avec des performances imprévisibles mais à des coûts financiers abordables. En outre, dans un environnement de cloud, les défaillances sont perçues comme étant ordinaires. Pour surmonter les limites d’un cloud individuel, plusieurs clouds peuvent être combinés pour former une fédération de clouds, souvent avec des coûts supplémentaires légers pour les utilisateurs. Une fédération de clouds peut aider autant les fournisseurs que les utilisateurs à atteindre leurs objectifs tels la réduction du temps d’exécution, la minimisation des coûts, l’augmentation de la disponibilité, la réduction de la consummation d’énergie, pour ne citer que ceux-là. Ainsi, la fédération de clouds peut être une solution élégante pour éviter le sur-approvisionnement, réduisant ainsi les coûts d’exploitation en situation de charge moyenne, et en supprimant des ressources qui, autrement, resteraient inutilisées et gaspilleraient ainsi de énergie. Cependant, la fédération de clouds élargit la gamme des ressources disponibles. En conséquence, pour les utilisateurs, des compétences en cloud computing ou en administration système sont nécessaires, ainsi qu’un temps d’apprentissage considérable pour maîtrises les options disponibles. Dans ce contexte, certaines questions se posent : (a) Quelle ressource du cloud est appropriée pour une application donnée ? (b) Comment les utilisateurs peuvent-ils exécuter leurs applications HPC avec un rendement acceptable et des coûts financiers abordables, sans avoir à reconfigurer les applications pour répondre aux norms et contraintes du cloud ? (c) Comment les non-spécialistes du cloud peuvent-ils maximiser l’usage des caractéristiques du cloud, sans être liés au fournisseur du cloud ? et (d) Comment les fournisseurs de cloud peuvent-ils exploiter la fédération pour réduire la consommation électrique, tout en étant en mesure de fournir un service garantissant les normes de qualité préétablies ? À partir de ces questions, la presente thèse propose une solution de consolidation d’applications pour la fédération de clouds qui garantit le respect des normes de qualité de service. On utilise un système multi-agents (SMA) pour négocier la migration des machines virtuelles entre les clouds. Les résultats de simulations montrent que notre approche pourrait réduire jusqu’à 46% la consommation totale d’énergie, tout en respectant les exigencies de performance. En nous basant sur la fédération de clouds, nous avons développé et évalué une approche pour exécuter une énorme application de bioinformatique à coût zéro. En outre, nous avons pu réduire le temps d’exécution de 22,55% par rapport à la meilleure exécution dans un cloud individuel. Cette thèse présente aussi une architecture de cloud baptisée « Excalibur » qui permet l’adaptation automatique des applications standards pour le cloud. Dans l’exécution d’une chaîne de traitements de la génomique, Excalibur a pu parfaitement mettre à l’échelle les applications sur jusqu’à 11 machines virtuelles, ce qui a réduit le temps d’exécution de 63% et le coût de 84% par rapport à la configuration de l’utilisateur. Enfin, cette thèse présente un processus d’ingénierie des lignes de produits (PLE) pour gérer la variabilité de l’infrastructure à la demande du cloud, et une architecture multi-cloud autonome qui utilise ce processus pour configurer et faire face aux défaillances de manière indépendante. Le processus PLE utilise le modele étendu de fonction (EFM) avec des attributs pour décrire les ressources et les sélectionner en fonction dês objectifs de l’utilisateur. Les expériences réalisées avec deux fournisseurs de cloud différents montrent qu’em utilisant le modèle proposé, les utilisateurs peuvent exécuter leurs applications dans un environnement de clouds fédérés, sans avoir besoin de connaître les variabilités et contraintes du cloud.

Le cloud computing a été considéré comme une option pour exécuter des applications de calcul haute performance. Bien que les plateformes traditionnelles de calcul haute performance telles que les grilles et les supercalculateurs offrent un environnement stable du point de vue des défaillances, des performances, et de la taille des ressources, le cloud computing offre des ressources à la demande, généralement avec des performances imprévisibles mais à des coûts financiers abordables. Pour surmonter les limites d’un cloud individuel, plusieurs clouds peuvent être combinés pour former une fédération de clouds, souvent avec des coûts supplémentaires légers pour les utilisateurs. Une fédération de clouds peut aider autant les fournisseurs que les utilisateurs à atteindre leurs objectifs tels la réduction du temps d’exécution, la minimisation des coûts, l’augmentation de la disponibilité, la réduction de la consommation d’énergie, pour ne citer que ceux-Là. Ainsi, la fédération de clouds peut être une solution élégante pour éviter le sur-Approvisionnement, réduisant ainsi les coûts d’exploitation en situation de charge moyenne, et en supprimant des ressources qui, autrement, resteraient inutilisées et gaspilleraient ainsi de énergie. Cependant, la fédération de clouds élargit la gamme des ressources disponibles. En conséquence, pour les utilisateurs, des compétences en cloud computing ou en administration système sont nécessaires, ainsi qu’un temps d’apprentissage considérable pour maîtrises les options disponibles. Dans ce contexte, certaines questions se posent: (a) Quelle ressource du cloud est appropriée pour une application donnée? (b) Comment les utilisateurs peuvent-Ils exécuter leurs applications HPC avec un rendement acceptable et des coûts financiers abordables, sans avoir à reconfigurer les applications pour répondre aux normes et contraintes du cloud ? (c) Comment les non-Spécialistes du cloud peuvent-Ils maximiser l’usage des caractéristiques du cloud, sans être liés au fournisseur du cloud ? et (d) Comment les fournisseurs de cloud peuvent-Ils exploiter la fédération pour réduire la consommation électrique, tout en étant en mesure de fournir un service garantissant les normes de qualité préétablies ? À partir de ces questions, la présente thèse propose une solution de consolidation d’applications pour la fédération de clouds qui garantit le respect des normes de qualité de service. On utilise un système multi-Agents pour négocier la migration des machines virtuelles entre les clouds. En nous basant sur la fédération de clouds, nous avons développé et évalué une approche pour exécuter une énorme application de bioinformatique à coût zéro. En outre, nous avons pu réduire le temps d’exécution de 22,55% par rapport à la meilleure exécution dans un cloud individuel. Cette thèse présente aussi une architecture de cloud baptisée « Excalibur » qui permet l’adaptation automatique des applications standards pour le cloud. Dans l’exécution d’une chaîne de traitements de la génomique, Excalibur a pu parfaitement mettre à l’échelle les applications sur jusqu’à 11 machines virtuelles, ce qui a réduit le temps d’exécution de 63% et le coût de 84% par rapport à la configuration de l’utilisateur. Enfin, cette thèse présente un processus d’ingénierie des lignes de produits (PLE) pour gérer la variabilité de l’infrastructure à la demande du cloud, et une architecture multi-Cloud autonome qui utilise ce processus pour configurer et faire face aux défaillances de manière indépendante. Le processus PLE utilise le modèle étendu de fonction avec des attributs pour décrire les ressources et les sélectionner en fonction des objectifs de l’utilisateur. Les expériences réalisées avec deux fournisseurs de cloud différents montrent qu’en utilisant le modèle proposé, les utilisateurs peuvent exécuter leurs applications dans un environnement de clouds fédérés, sans avoir besoin de connaître les variabilités et contraintes du cloud<br>Cloud computing has been seen as an option to execute high performance computing (HPC) applications. While traditional HPC platforms such as grid and supercomputers offer a stable environment in terms of failures, performance, and number of resources, cloud computing offers on-Demand resources generally with unpredictable performance at low financial cost. Furthermore, in cloud environment, failures are part of its normal operation. To overcome the limits of a single cloud, clouds can be combined, forming a cloud federation often with minimal additional costs for the users. A cloud federation can help both cloud providers and cloud users to achieve their goals such as to reduce the execution time, to achieve minimum cost, to increase availability, to reduce power consumption, among others. Hence, cloud federation can be an elegant solution to avoid over provisioning, thus reducing the operational costs in an average load situation, and removing resources that would otherwise remain idle and wasting power consumption, for instance. However, cloud federation increases the range of resources available for the users. As a result, cloud or system administration skills may be demanded from the users, as well as a considerable time to learn about the available options. In this context, some questions arise such as: (a) which cloud resource is appropriate for a given application? (b) how can the users execute their HPC applications with acceptable performance and financial costs, without needing to re-Engineer the applications to fit clouds' constraints? (c) how can non-Cloud specialists maximize the features of the clouds, without being tied to a cloud provider? and (d) how can the cloud providers use the federation to reduce power consumption of the clouds, while still being able to give service-Level agreement (SLA) guarantees to the users? Motivated by these questions, this thesis presents a SLA-Aware application consolidation solution for cloud federation. Using a multi-Agent system (MAS) to negotiate virtual machine (VM) migrations between the clouds, simulation results show that our approach could reduce up to 46% of the power consumption, while trying to meet performance requirements. Using the federation, we developed and evaluated an approach to execute a huge bioinformatics application at zero-Cost. Moreover, we could decrease the execution time in 22.55% over the best single cloud execution. In addition, this thesis presents a cloud architecture called Excalibur to auto-Scale cloud-Unaware application. Executing a genomics workflow, Excalibur could seamlessly scale the applications up to 11 virtual machines, reducing the execution time by 63% and the cost by 84% when compared to a user's configuration. Finally, this thesis presents a product line engineering (PLE) process to handle the variabilities of infrastructure-As-A-Service (IaaS) clouds, and an autonomic multi-Cloud architecture that uses this process to configure and to deal with failures autonomously. The PLE process uses extended feature model (EFM) with attributes to describe the resources and to select them based on users' objectives. Experiments realized with two different cloud providers show that using the proposed model, the users could execute their application in a cloud federation environment, without needing to know the variabilities and constraints of the clouds

This research proposes an architecture for a cloud-based, multi-user FEA pre-processing system, where multiple engineers can access and operate on the same model in a parallel environment. A prototype is discussed and tested, the results of which show that a multi-user preprocessor, where all computing is done on a central server that is hosted on a high performance system, provides significant benefits to the analysis team. These benefits include a shortened preprocessing time, and potentially higher-quality models.

Il Cloud Computing è emerso recentemente come una tecnologia dirompente per la gestione dei servizi IT su Internet, evolvendosi attraverso diverse fasi da Grid Computing, Utility Computing e Software-as-a-Service (SaaS). Nonostante un iniziale scetticismo, le aziende internazionali stanno ora migrando consistentemente il carico di lavoro IT su soluzioni Cloud private e pubbliche per ottimizzare la copertura geografica e lanciare nuovi servizi digitali. Tuttavia, il dinamismo dei sistemi e la creazione di ambienti Hybrid e Multi-Cloud introducono ulteriore complessità nella gestione della Qualità dei Servizi (QoS) e richiedono la definizione di Service Level Agreement (SLA) standard e approcci strutturati. Lo scopo della ricerca è valutare la maturità delle attuali tecniche regolate da SLA e definire un meta-modello per coprire l'intero ciclo di vita della gestione degli SLA stessi. Per analizzare a fondo lo stato dell'arte, la ricerca ha valutato le migliori pratiche di gestione dello SLA del Cloud attraverso una revisione della letteratura strutturata e ha identificato le principali esigenze aziendali attraverso un'indagine su diverse società internazionali. L'analisi evidenzia chiaramente una lacuna nella gestione degli SLA in ambienti Hybrid e Multi-Cloud che sta limitando il controllo della QoS all'utilizzo del sistema di monitoraggio dei fornitori di servizi cloud (CSP). Inoltre, i principali framework di gestione IT (cioè ITIL e COBIT) sono ancora basati sulla possibilità di interagire direttamente con i sistemi IT e, per questo motivo, non concepiti per il Cloud Computing. Partendo da questi risultati, la ricerca ha definito un framework SLA-aware, chiamato LISA, per evitare violazioni dello SLA e supportare sia i consumatori che i provider nell'intero ciclo di vita della gestione degli SLA in ambienti Multi-Cloud. Le prestazioni del framework sono state testate nel laboratorio di innovazione di un operatore di telecomunicazioni globale, implementando servizi su soluzioni cloud private e provider di servizi cloud pubblici. I risultati sperimentali convalidano l'efficienza di LISA nell'impedire violazioni dello SLA e degrado delle prestazioni del servizio, ottimizzando la QoS e il livello di controllo sui componenti del servizio implementati tra più provider di servizi cloud pubblici.<br>Cloud Computing recently emerged as a disruptive technology for managing IT services over the Internet, evolving through different phases from Grid Computing, Utility Computing and Software-as-a-Service (SaaS). Despite an initial scepticism, international companies are now widely migrating the IT workload on private and public Cloud solutions to optimise the geographical coverage and launch new digital services. However, the dynamism of the systems and the creation of hybrid and Multi-Cloud environments introduce additional complexity in managing the Quality of Services (QoS) and require the definition of standard Service Level Agreements (SLAs) and structured approaches. The aim of the research is to evaluate the maturity of the current SLA driven techniques and define a meta-model to cover the entire SLA management lifecycle. To deeply analyse the state of the art, the research evaluated the available Cloud SLA management best practices through a structured literature review and identified the main business needs through a survey on several international companies. The analysis clearly highlights a gap in the SLA management in hybrid and Multi-Cloud environments that is confining the control of the QoS to the use of the Cloud Service Providers (CSPs) monitoring system. Moreover, the main IT management frameworks (i.e. ITIL and COBIT) are still based on the possibility to directly interact with the IT systems and, for this reason, not conceived for Cloud Computing. Starting from these findings, the research defined a SLA-aware framework, called LISA, to avoid SLA violations and support both consumers and providers across the entire SLA management lifecycle in Multi-Cloud environments. The performance of the framework has been tested in the Innovation lab of a global telco operator, deploying services on private Cloud solutions and public Cloud providers. The experimental results validate the efficiency of LISA in preventing SLA violations and service performance degradations, optimising the QoS and the degree of control on service’ components deployed across multiple public Cloud providers.

The PrEstoCloud project aims to enable on-demand resource scaling of Big Data applications to the cloud. In this context, we have to deal with the huge amount of data processed and more, in particular, its transportation between one cloud and another. The scope of this thesis is to develop a network-level architecture that could easily deal with Big Data application challenges and could be integrated into the PrEstoCloud consortium staying transparent to the application level. However, the connection between multiple cloud providers in this context presents a series of challenges: the architecture should adapt to the variable number of clouds to connect, it have to bypass the limitations of the cloud infrastructure and most importantly, it must have a general design able to work in every cloud provider. In this report, we present a general VPN-based Inter-Cloud architecture able to work in every kind of environment. We implemented a prototype with IPSec and OpenVPN, connecting the i3s laboratory with Amazon AWS and Azure, we evaluate our architecture and the used tools in two ways: (i) we test the stability over time of the architecture via latency tests; (ii) we perform non-intrusive Pathload tests in the Amazon, showing the usability of the available bandwidth estimator in the cloud, the AWS network characteristics discovered through the tests and a final comparison of the VPN tools overhead.

Cloud brokering facilitates CSUs to find cloud services according to their requirements. In the current practice, CSUs or Cloud Service Brokers (CSBs) select cloud services according to SLA committed by CSPs in their website. In our observation, it is found that most of the CSPs do not fulfill the service commitment mentioned in the SLA agreement. Verified cloud service performances against their SLA commitment of CSPs provide an additional trust on CSBs to recommend services to the CSUs. In this thesis work, we propose a SLA assured service-brokering framework, which considers both committed and delivered SLA by CSPs in cloud service recommendation to the users. For the evaluation of the performance of CSPs, two evaluation techniques: Heat Map and IFL are proposed, which include both directly measurable and non-measurable parameters in the performance evaluation CSPs. These two techniques are implemented using real data measured from CSPs. The result shows that Heat Map technique is more transparent and consistent in CSP performance evaluation than IFL technique. In this work, regulatory compliance of the CSPs is also analyzed and visualized in performance heat map table to provide legal status of CSPs. Moreover, missing points in their terms of service and SLA document are analyzed and recommended to add in the contract document. In the revised European GPDR, DPIA is going to be mandatory for all organizations/tools. The decision recommendation tool developed using above mentioned evaluation techniques may cause potential harm to individuals in assessing data from multiple CSPs. So, DPIA is carried out to assess the potential harm/risks to individuals due to our tool and necessary precaution to be taken in the tool to minimize possible data privacy risks. It also analyzes the service pattern and future performance behavior of CSPs to help CSUs in decision making to select appropriate CSP.

Cloud computing represents a fundamental change in the way organizations acquire technological resources (e.g., hardware, development and execution environments, applications); where, instead of buying them, they acquire remote access to them in the form of cloud services supplied through the Internet. Among the main characteristics of cloud computing is the allocation of resources in an agile and elastic way, reserved or released depending on the demand of the users or applications, enabling the payment model based on consumption metrics. The development of cloud applications mostly follows an incremental approach, where the incremental delivery of functionalities to the client changes - or reconfigures - successively the current architecture of the application. Cloud providers have their own standards for both implementation technologies and service management mechanisms, requiring solutions that facilitate: building, integrating and deploying portable services; interoperability between services deployed across different cloud providers; and continuity In the execution of the application while its architecture is reconfigured product of the integration of the successive increments. The principles of the model-driven development approach, the architectural style service-oriented architectures, and the dynamic reconfiguration play an important role in this context. The hypothesis of this doctoral thesis is that model-driven development methods provide cloud service developers with abstraction and automation mechanisms for the systematic application of the principles of model engineering during the design, implementation, and incremental deployment of cloud services, facilitating the dynamic reconfiguration of the service-oriented architecture of cloud applications. The main objective of this doctoral thesis is therefore to define and validate empirically DIARy, a method of dynamic and incremental reconfiguration of service-oriented architectures for cloud applications. This method will allow specifying the architectural integration of the increment with the current cloud application, and with this information to automate the derivation of implementation artifacts that facilitate the integration and dynamic reconfiguration of the service architecture of the cloud application. This dynamic reconfiguration is achieved by running reconfiguration artifacts that not only deploy / un-deploy increment's services and orchestration services between services of the increment with the services of the current cloud application; but also, they change the links between services at runtime. A software infrastructure that supports the activities of the proposed method has also been designed and implemented. The software infrastructure includes the following components: i) a set of DSLs, with their respective graphical editors, that allow to describe aspects related to the architectural integration, implementation and provisioning of increments in cloud environments; ii) transformations that generate platform-specific implementation and provisioning models; (iii) transformations that generate artifacts that implement integration logic and orchestration of services, and scripts of provisioning, deployment, and dynamic reconfiguration for different cloud vendors. This doctoral thesis contributes to the field of service-oriented architectures and in particular to the dynamic reconfiguration of cloud services architectures in an iterative and incremental development context. The main contribution is a well-defined method, based on the principles of model-driven development, which makes it easy to raise the level of abstraction and automate, through transformations, the generation of artifacts that perform the dynamic reconfiguration of cloud applications.<br>La computación cloud representa un cambio fundamental en la manera en la que las organizaciones adquieren recursos tecnológicos (p. ej., hardware, entornos de desarrollo y ejecución, aplicaciones); en donde, en lugar de comprarlos adquieren acceso remoto a ellos en forma de servicios cloud suministrados a través de Internet. Entre las principales características de la computación cloud está la asignación de recursos de manera ágil y elástica, reservados o liberados dependiendo de la demanda de los usuarios o aplicaciones, posibilitando el modelo de pago basado en métricas de consumo. El desarrollo de aplicaciones cloud sigue mayoritariamente un enfoque incremental, en donde la entrega incremental de funcionalidades al cliente cambia - o reconfigura - sucesivamente la arquitectura actual de la aplicación. Los proveedores cloud tienen sus propios estándares tanto para las tecnologías de implementación como para los mecanismos de gestión de servicios, requiriéndose soluciones que faciliten: la construcción, integración y despliegue de servicios portables; la interoperabilidad entre servicios desplegados en diferentes proveedores cloud; y la continuidad en la ejecución de la aplicación mientras su arquitectura es reconfigurada producto de la integración de los sucesivos incrementos. Los principios del enfoque de desarrollo dirigido por modelos, del estilo arquitectónico de arquitecturas orientadas a servicios y de la reconfiguración dinámica cumplen un papel importante en este contexto. La hipótesis de esta tesis doctoral es que los métodos de desarrollo dirigido por modelos brindan a los desarrolladores de servicios cloud mecanismos de abstracción y automatización para la aplicación sistemática de los principios de la ingeniería de modelos durante el diseño, implementación y despliegue incremental de servicios cloud, facilitando la reconfiguración dinámica de la arquitectura orientada a servicios de las aplicaciones cloud. El objetivo principal de esta tesis doctoral es por tanto definir y validar empíricamente DIARy, un método de reconfiguración dinámica e incremental de arquitecturas orientadas a servicios. Este método permitirá especificar la integración arquitectónica del incremento con la aplicación cloud actual, y con esta información automatizar la derivación de los artefactos de implementación que faciliten la integración y reconfiguración dinámica de la arquitectura de servicios de la aplicación cloud. Esta reconfiguración dinámica se consigue al ejecutar los artefactos de reconfiguración que no solo despliegan/repliegan los servicios del incremento y servicios de orquestación entre los servicios del incremento con los servicios de la aplicación cloud actual; sino también, cambian en tiempo de ejecución los enlaces entre servicios. También se ha diseñado e implementado una infraestructura software que soporta las actividades del método propuesto e incluye los siguientes componentes: i) un conjunto de DSLs, con sus respectivos editores gráficos, que permiten describir aspectos relacionados a la integración arquitectónica, implementación y aprovisionamiento de incrementos en entornos cloud; ii) transformaciones que generan modelos de implementación y aprovisionamiento; iii) transformaciones que generan artefactos que implementan la lógica de integración y orquestación de servicios, y scripts de aprovisionamiento, despliegue y reconfiguración dinámica específicos para distintos proveedores cloud. Esta tesis doctoral contribuye al campo de las arquitecturas orientadas a servicios y en particular a la reconfiguración dinámica de arquitecturas de servicios cloud en contextos de desarrollo iterativo e incremental. El principal aporte es un método bien definido, basado en los principios del desarrollo dirigido por modelos, que facilita elevar el nivel de abstracción y automatizar por medio de transformaciones la generación de artefactos que real<br>La computació cloud representa un canvi fonamental en la manera en què les organitzacions adquirixen recursos tecnològics (ej., maquinari, entorns de desplegament i execució, aplicacions) ; on, en compte de comprar-los adquirixen accés remot a ells en forma de servicis cloud subministrats a través d'Internet. Entre les principals característiques de la computació cloud els recursos cloud són assignats de manera àgil i elàstica, reservats o alliberats depenent de la demanda dels usuaris o aplicacions, possibilitant el model de pagament basat en mètriques de consum. El desenrotllament d'aplicacions cloud seguix majoritàriament un enfocament incremental, on l'entrega incremental de funcionalitats al client canvia - o reconfigura - successivament l'arquitectura actual de l'aplicació. Els proveïdors cloud tenen els seus propis estàndards tant per a les tecnologies d'implementació com per als mecanismes de gestió de servicis, requerint-se solucions que faciliten: la construcció, integració i desplegament de servicis portables; la interoperabilitat entre servicis desplegats en diferents proveïdors cloud; i la continuïtat en l'execució de l'aplicació mentres la seua arquitectura és reconfigurada producte de la integració dels successius increments. Els principis de l'enfocament de desenrotllament dirigit per models, de l'estil arquitectònic d'arquitectures orientades a servicis i de la reconfiguració dinàmica complixen un paper important en este context. La hipòtesi d'esta tesi doctoral és que els mètodes de desenrotllament dirigit per models brinden als desenvolupadors de servicis cloud mecanismes d'abstracció i automatització per a l'aplicació sistemàtica dels principis de l'enginyeria de models durant el disseny, implementació i desplegament incremental de servicis cloud, facilitant la reconfiguració dinàmica de l'arquitectura orientada a servicis de les aplicacions cloud. L'objectiu principal d'esta tesi doctoral és per tant de definir i validar empí-ricamente DIARy, un mètode de reconfiguració dinàmica i incremental d'arquitectures orientades a servicis per a aplicacions cloud. Este mètode permetrà especificar la integració arquitectònica de l'increment amb l'aplicació cloud actual, i amb esta informació automatitzar la derivació dels artefactes d'implementació que faciliten la integració i reconfiguració dinàmica de l'arquitectura de servicis de l'aplicació cloud. Esta reconfi-guración dinàmica s'aconseguix a l'executar els artefactes de reconfiguració que no sols despleguen/repleguen els servicis de l'increment i servicis d'orquestració entre els servicis de l'increment amb els servicis de l'aplicació cloud actual; sinó també, canvien en temps d'execució els enllaços entre servicis. També s'ha dissenyat i implementat una infraestructura programari que suporta les activitats del mètode proposat i inclou els següents components: i) un conjunt de DSLs, amb els seus respectius editors gràfics, que permeten descriure aspectes relacionats a la integració arquitectònica, implementació i aprovisionament en entorns cloud dels increments; ii) transformacions que generen models d'implementació i aprovisionament específics de la plataforma a partir dels models d'integració d'alt nivell; iii) transformacions que generen artefactes que implementen la lògica d'integració i orquestració de servicis, i scripts d'aprovisionament, desplegament i reconfiguració dinàmica específics per a distints proveïdors cloud. Esta tesi doctoral contribuïx al camp de les arquitectures orientades a servicis i en particular a la reconfiguració dinàmica d'arquitectures de servicis cloud en contextos de desenrotllament iteratiu i incremental. La principal aportació és un mètode ben definit, basat en els principis del desenrotllament dirigit per models, que facilita elevar el nivell d'abstracció i automatitzar per mitjà de transformacions la generació d'artefactes que r<br>Zuñiga Prieto, MÁ. (2017). Reconfiguración Dinámica e Incremental de Arquitecturas de Servicios Cloud Dirigida por Modelos [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/86288<br>TESIS

This thesis discusses the new way of delivering IT services over the Internet widely known as cloud computing. In its opening part, cloud computing is put into a historical context of the evolution of enterprise computing, and the dominant issues the IT department faces today are mentioned. Further, the paper deals with several components that make up the architecture of cloud computing and reviews the benefits and drawbacks an enterprise can have while it adopts this new model. One of the primary aims of this thesis is to identify the impact of the technology trends on cloud computing. The thesis brings together four major computing trends, namely virtualization, multi-tenant architecture, service-oriented architecture and grid computing. Another aim is to focus on two trends related to IT infrastructure that will lead to fundamental changes in IT industry. The first of them is the emergence of extremely large-scale data centers at low cost locations, which can serve tremendous amount of customers and achieve considerable economies of scale. The second trend this paper points out is the shift from multi-purpose all-in-one computers into a wide range of mobile devices dedicated to a specific user's needs. The last aim of this thesis is to clarify the economic impact of cloud computing in terms of costs and changes in business models. The thesis concludes by evaluating the current adoption and predicting the future trend of cloud computing.

Malgré de nombreuses années de travail en robotique, il existe toujours un manque d’architecture logicielle et de middleware stables pour les systèmes multi-robot. Un intergiciel robotique devrait être conçu pour faire abstraction de l’architecture matérielle de bas niveau, faciliter la communication et l’intégration de nouveaux logiciels. Cette thèse se concentre sur le middleware pour systèmes multi-robot et sur la façon dont nous pouvons améliorer les frameworks existantes dans un contexte multi-robot en ajoutant des services de coordination multi-robot, des outils de développement et de déploiement massif. Nous nous attendons à ce que les robots soient de plus en plus utiles car ils peuvent tirer profit des données provenant d’autres périphériques externes dans leur prise de décision au lieu de simplement réagir à leur environnement local (capteurs, robots coopérant dans une flotte, etc.). Cette thèse évalue d’abord l’un des intergiciels les plus récents pour robot(s) mobile(s), Robot operating system (ROS), suivi par la suite d’un état de l’art sur les middlewares couramment utilisés en robotique. Basé sur les conclusions, nous proposons une contribution originale dans le contexte multi-robots, appelé SDfR (Service discovery for Robots), un mécanisme de découverte des services pour les robots. L’objectif principal est de proposer un mécanisme permettant aux robots de garder une trace des pairs accessibles à l’intérieur d’une flotte tout en utilisant une infrastructure ad-hoc. A cause de la mobilité des robots, les techniques classiques de configuration de réseau pair à pair ne conviennent pas. SDfR est un protocole hautement dynamique, adaptatif et évolutif adapté du protocole SSDP (Simple Service Discovery Protocol). Nous conduisons un ensemble d’expériences, en utilisant une flotte de robots Turtlebot, pour mesurer et montrer que le surdébit de SDfR est limité. La dernière partie de la thèse se concentre sur un modèle de programmation basé sur un automate temporisé. Ce type de programmation a l’avantage d’avoir un modèle qui peut être vérifié et simulé avant de déployer l’application sur de vrais robots. Afin d’enrichir et de faciliter le développement d’applications robotiques, un nouveau modèle de programmation basé sur des automates à états temporisés est proposé, appelé ROSMDB (Robot Operating system Model Driven Behaviour). Il fournit une vérification de modèle lors de la phase de développement et lors de l’exécution. Cette contribution est composée de plusieurs composants : une interface graphique pour créer des modèles basés sur un automate temporisé, un vérificateur de modèle intégré basé sur UPPAAL et un générateur de squelette de code. Enfin, nous avons effectué deux expériences : une avec une flotte de drones Parrot et l’autre avec des Turtlebots afin d’illustre le modèle proposé et sa capacité à vérifier les propriétés<br>Despite many years of work in robotics, there is still a lack of established software architecture and middleware for multi-robot systems. A robotic middleware should be designed to abstract the low-level hardware architecture, facilitate communication and integration of new software. This PhD thesis is focusing on middleware for multi-robot system and how we can improve existing frameworks for fleet purposes by adding multi-robot coordination services, development and massive deployment tools. We expect robots to be increasingly useful as they can take advantage of data pushed from other external devices in their decision making instead of just reacting to their local environment (sensors, cooperating robots in a fleet, etc). This thesis first evaluates one of the most recent middleware for mobile robot(s), Robot operating system (ROS) and continues with a state of the art about the commonly used middlewares in robotics. Based on the conclusions, we propose an original contribution in the multi-robot context, called SDfR (Service discovery for Robots), a service discovery mechanism for Robots. The main goal is to propose a mechanism that allows highly mobile robots to keep track of the reachable peers inside a fleet while using an ad-hoc infrastructure. Another objective is to propose a network configuration negotiation protocol. Due to the mobility of robots, classical peer to peer network configuration techniques are not suitable. SDfR is a highly dynamic, adaptive and scalable protocol adapted from Simple Service Discovery Protocol (SSDP). We conduced a set of experiments, using a fleet of Turtlebot robots, to measure and show that the overhead of SDfR is limited. The last part of the thesis focuses on programming model based on timed automata. This type of programming has the benefits of having a model that can be verified and simulated before deploying the application on real robots. In order to enrich and facilitate the development of robotic applications, a new programming model based on timed automata state machines is proposed, called ROSMDB (Robot Operating system Model Driven Behaviour). It provides model checking at development phase and at runtime. This contribution is composed of several components: a graphical interface to create models based on timed automata, an integrated model checker based on UPPAAL and a code skeleton generator. Moreover, a ROS specific framework is proposed to verify the correctness of the execution of the models and to trigger alerts. Finally, we conduct two experiments: one with a fleet of Parrot drones and second with Turtlebots in order to illustrates the proposed model and its ability to check properties

Tesis por compendio<br>[ES] Las aplicaciones científicas implican generalmente una carga computacional variable y no predecible a la que las instituciones deben hacer frente variando dinámicamente la asignación de recursos en función de las distintas necesidades computacionales. Las aplicaciones científicas pueden necesitar grandes requisitos. Por ejemplo, una gran cantidad de recursos computacionales para el procesado de numerosos trabajos independientes (High Throughput Computing o HTC) o recursos de alto rendimiento para la resolución de un problema individual (High Performance Computing o HPC). Los recursos computacionales necesarios en este tipo de aplicaciones suelen acarrear un coste muy alto que puede exceder la disponibilidad de los recursos de la institución o estos pueden no adaptarse correctamente a las necesidades de las aplicaciones científicas, especialmente en el caso de infraestructuras preparadas para la ejecución de aplicaciones de HPC. De hecho, es posible que las diferentes partes de una aplicación necesiten distintos tipos de recursos computacionales. Actualmente las plataformas de servicios en la nube se han convertido en una solución eficiente para satisfacer la demanda de las aplicaciones HTC, ya que proporcionan un abanico de recursos computacionales accesibles bajo demanda. Por esta razón, se ha producido un incremento en la cantidad de clouds híbridos, los cuales son una combinación de infraestructuras alojadas en servicios en la nube y en las propias instituciones (on-premise). Dado que las aplicaciones pueden ser procesadas en distintas infraestructuras, actualmente la portabilidad de las aplicaciones se ha convertido en un aspecto clave. Probablemente, las tecnologías de contenedores son la tecnología más popular para la entrega de aplicaciones gracias a que permiten reproducibilidad, trazabilidad, versionado, aislamiento y portabilidad. El objetivo de la tesis es proporcionar una arquitectura y una serie de servicios para proveer infraestructuras elásticas híbridas de procesamiento que puedan dar respuesta a las diferentes cargas de trabajo. Para ello, se ha considerado la utilización de elasticidad vertical y horizontal desarrollando una prueba de concepto para proporcionar elasticidad vertical y se ha diseñado una arquitectura cloud elástica de procesamiento de Análisis de Datos. Después, se ha trabajo en una arquitectura cloud de recursos heterogéneos de procesamiento de imágenes médicas que proporciona distintas colas de procesamiento para trabajos con diferentes requisitos. Esta arquitectura ha estado enmarcada en una colaboración con la empresa QUIBIM. En la última parte de la tesis, se ha evolucionado esta arquitectura para diseñar e implementar un cloud elástico, multi-site y multi-tenant para el procesamiento de imágenes médicas en el marco del proyecto europeo PRIMAGE. Esta arquitectura utiliza un almacenamiento distribuido integrando servicios externos para la autenticación y la autorización basados en OpenID Connect (OIDC). Para ello, se ha desarrollado la herramienta kube-authorizer que, de manera automatizada y a partir de la información obtenida en el proceso de autenticación, proporciona el control de acceso a los recursos de la infraestructura de procesamiento mediante la creación de las políticas y roles. Finalmente, se ha desarrollado otra herramienta, hpc-connector, que permite la integración de infraestructuras de procesamiento HPC en infraestructuras cloud sin necesitar realizar cambios en la infraestructura HPC ni en la arquitectura cloud. Cabe destacar que, durante la realización de esta tesis, se han utilizado distintas tecnologías de gestión de trabajos y de contenedores de código abierto, se han desarrollado herramientas y componentes de código abierto y se han implementado recetas para la configuración automatizada de las distintas arquitecturas diseñadas desde la perspectiva DevOps.<br>[CA] Les aplicacions científiques impliquen generalment una càrrega computacional variable i no predictible a què les institucions han de fer front variant dinàmicament l'assignació de recursos en funció de les diferents necessitats computacionals. Les aplicacions científiques poden necessitar grans requisits. Per exemple, una gran quantitat de recursos computacionals per al processament de nombrosos treballs independents (High Throughput Computing o HTC) o recursos d'alt rendiment per a la resolució d'un problema individual (High Performance Computing o HPC). Els recursos computacionals necessaris en aquest tipus d'aplicacions solen comportar un cost molt elevat que pot excedir la disponibilitat dels recursos de la institució o aquests poden no adaptar-se correctament a les necessitats de les aplicacions científiques, especialment en el cas d'infraestructures preparades per a l'avaluació d'aplicacions d'HPC. De fet, és possible que les diferents parts d'una aplicació necessiten diferents tipus de recursos computacionals. Actualment les plataformes de servicis al núvol han esdevingut una solució eficient per satisfer la demanda de les aplicacions HTC, ja que proporcionen un ventall de recursos computacionals accessibles a demanda. Per aquest motiu, s'ha produït un increment de la quantitat de clouds híbrids, els quals són una combinació d'infraestructures allotjades a servicis en el núvol i a les mateixes institucions (on-premise). Donat que les aplicacions poden ser processades en diferents infraestructures, actualment la portabilitat de les aplicacions s'ha convertit en un aspecte clau. Probablement, les tecnologies de contenidors són la tecnologia més popular per a l'entrega d'aplicacions gràcies al fet que permeten reproductibilitat, traçabilitat, versionat, aïllament i portabilitat. L'objectiu de la tesi és proporcionar una arquitectura i una sèrie de servicis per proveir infraestructures elàstiques híbrides de processament que puguen donar resposta a les diferents càrregues de treball. Per a això, s'ha considerat la utilització d'elasticitat vertical i horitzontal desenvolupant una prova de concepte per proporcionar elasticitat vertical i s'ha dissenyat una arquitectura cloud elàstica de processament d'Anàlisi de Dades. Després, s'ha treballat en una arquitectura cloud de recursos heterogenis de processament d'imatges mèdiques que proporciona distintes cues de processament per a treballs amb diferents requisits. Aquesta arquitectura ha estat emmarcada en una col·laboració amb l'empresa QUIBIM. En l'última part de la tesi, s'ha evolucionat aquesta arquitectura per dissenyar i implementar un cloud elàstic, multi-site i multi-tenant per al processament d'imatges mèdiques en el marc del projecte europeu PRIMAGE. Aquesta arquitectura utilitza un emmagatzemament integrant servicis externs per a l'autenticació i autorització basats en OpenID Connect (OIDC). Per a això, s'ha desenvolupat la ferramenta kube-authorizer que, de manera automatitzada i a partir de la informació obtinguda en el procés d'autenticació, proporciona el control d'accés als recursos de la infraestructura de processament mitjançant la creació de les polítiques i rols. Finalment, s'ha desenvolupat una altra ferramenta, hpc-connector, que permet la integració d'infraestructures de processament HPC en infraestructures cloud sense necessitat de realitzar canvis en la infraestructura HPC ni en l'arquitectura cloud. Es pot destacar que, durant la realització d'aquesta tesi, s'han utilitzat diferents tecnologies de gestió de treballs i de contenidors de codi obert, s'han desenvolupat ferramentes i components de codi obert, i s'han implementat receptes per a la configuració automatitzada de les distintes arquitectures dissenyades des de la perspectiva DevOps.<br>[EN] Scientific applications generally imply a variable and an unpredictable computational workload that institutions must address by dynamically adjusting the allocation of resources to their different computational needs. Scientific applications could require a high capacity, e.g. the concurrent usage of computational resources for processing several independent jobs (High Throughput Computing or HTC) or a high capability by means of using high-performance resources for solving complex problems (High Performance Computing or HPC). The computational resources required in this type of applications usually have a very high cost that may exceed the availability of the institution's resources or they are may not be successfully adapted to the scientific applications, especially in the case of infrastructures prepared for the execution of HPC applications. Indeed, it is possible that the different parts that compose an application require different type of computational resources. Nowadays, cloud service platforms have become an efficient solution to meet the need of HTC applications as they provide a wide range of computing resources accessible on demand. For this reason, the number of hybrid computational infrastructures has increased during the last years. The hybrid computation infrastructures are the combination of infrastructures hosted in cloud platforms and the computation resources hosted in the institutions, which are named on-premise infrastructures. As scientific applications can be processed on different infrastructures, the application delivery has become a key issue. Nowadays, containers are probably the most popular technology for application delivery as they ease reproducibility, traceability, versioning, isolation, and portability. The main objective of this thesis is to provide an architecture and a set of services to build up hybrid processing infrastructures that fit the need of different workloads. Hence, the thesis considered aspects such as elasticity and federation. The use of vertical and horizontal elasticity by developing a proof of concept to provide vertical elasticity on top of an elastic cloud architecture for data analytics. Afterwards, an elastic cloud architecture comprising heterogeneous computational resources has been implemented for medical imaging processing using multiple processing queues for jobs with different requirements. The development of this architecture has been framed in a collaboration with a company called QUIBIM. In the last part of the thesis, the previous work has been evolved to design and implement an elastic, multi-site and multi-tenant cloud architecture for medical image processing has been designed in the framework of a European project PRIMAGE. This architecture uses a storage integrating external services for the authentication and authorization based on OpenID Connect (OIDC). The tool kube-authorizer has been developed to provide access control to the resources of the processing infrastructure in an automatic way from the information obtained in the authentication process, by creating policies and roles. Finally, another tool, hpc-connector, has been developed to enable the integration of HPC processing infrastructures into cloud infrastructures without requiring modifications in both infrastructures, cloud and HPC. It should be noted that, during the realization of this thesis, different contributions to open source container and job management technologies have been performed by developing open source tools and components and configuration recipes for the automated configuration of the different architectures designed from the DevOps perspective. The results obtained support the feasibility of the vertical elasticity combined with the horizontal elasticity to implement QoS policies based on a deadline, as well as the feasibility of the federated authentication model to combine public and on-premise clouds.<br>López Huguet, S. (2021). Elastic, Interoperable and Container-based Cloud Infrastructures for High Performance Computing [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/172327<br>TESIS<br>Compendio

L'explosion du nombre d'utilisateurs d'Internet et du volume de trafic constitue un défi majeur pour la gestion efficace des réseaux de diffusion de contenu (CDN). Bien que ces réseaux aient amélioré leur temps de réponse en exploitant la mise en cache dans des serveurs cloud proches des utilisateurs, les services non mis en cache continuent de poser des problèmes de gestion de trafic. Pour répondre à cette problématique, les réseaux overlay cloud ont émergé, mais ils introduisent des complexités telles que les violations d'inégalités triangulaires (TIV). Dans ce contexte, l'application du paradigme des réseaux à définition logicielle (SDN) combinée aux techniques d'apprentissage par renforcement profond (DRL) offre une opportunité prometteuse pour s'adapter en temps réel aux fluctuations de l'environnement. Face à l'augmentation constante du nombre de serveurs edge, les solutions distribuées de DRL, notamment les modèles d'apprentissage par renforcement profond multi-agent (MA-DRL), deviennent cruciales. Cependant, ces modèles rencontrent des défis non résolus tels que l'absence de simulateurs réseau réalistes, le surcoût de communication entre agents et la convergence et stabilité.Cette thèse se concentre donc sur l'exploration des méthodes MA-DRL pour le routage de paquets dans les réseaux overlay cloud. Elle propose des solutions pour relever ces défis, notamment le développement de simulateurs de réseau réalistes, l'étude du surcoût de communication et la conception d'une solution MA-DRL adaptée aux réseaux overlay cloud. L'accent est mis sur le compromis entre la performance et la quantité d'information partagée entre les agents, ainsi que sur la convergence et la stabilité durant l'entraînement<br>The exponential growth of Internet traffic in recent decades has prompted the emergence of Content Delivery Networks (CDNs) as a solution for managing high traffic volumes through data caching in cloud servers located near end-users. However, challenges persist, particularly for non-cacheable services, necessitating the use of cloud overlay networks. Due to a lack of knowledge about the underlay network, cloud overlay networks introduce complexities such as Triangle inequality violations (TIV) and dynamic traffic routing challenges.Leveraging the Software Defined Networks (SDN) paradigm, Deep Reinforcement Learning (DRL) techniques offer the possibility to exploit collected data to better adapt to network changes. Furthermore, the increase of cloud edge servers presents scalability challenges, motivating the exploration of Multi-Agent DRL (MA-DRL) solutions. Despite its suitability for the distributed packet routing problem in cloud overlay networks, MA-DRL faces non-addressed challenges such as the need for realistic network simulators, handling communication overhead, and addressing the multi-objective nature of the routing problem.This Ph.D. thesis delves into the realm of distributed Multi-Agent Deep Reinforcement Learning (MA-DRL) methods, specifically targeting the Distributed Packet Routing problem in cloud overlay networks. Throughout the thesis, we address these challenges by developing realistic network simulators, studying communication overhead in the non-overlay general setting, and proposing a distributed MA-DRL framework tailored to cloud overlay networks, focusing on communication overhead, convergence, and model stability

Le Cloud Computing représente une des plus importantes avancées numériques de ces dix dernières années. Le modèle de service offert par le cloud computing est basé sur une allocation élastique et à la demande des ressources et une facturation au plus juste de leur utilisation. Plusieurs catégories d’application sont en train de migrer vers le cloud (par exemple : les NFV et les applications du Big Data). D’autres domaines applicatifs, soumis à une législation plus stricte, sont plus frileux. Leurs exigences sont souvent liées à des problématiques de sécurité et/ou à la non satisfaction par les ressources proposées par un cloud unique, peuvent trouver des réponses dans l’utilisation conjointe de plusieurs fournisseurs de cloud computing (CSPs). L’exploitation simultanée, flexible, efficace et simplifiée de plusieurs clouds requiert des propriétés qui assurent sa viabilité et son acceptation tout d’abord par les fournisseurs de clouds qui proposent des offres hétérogènes et non interopérables et qui souvent pour des raisons commerciales, ne sont pas disposés à coopérer pour faciliter le multi-cloud « à la carte » ; mais aussi du point de vue du consommateur de services cloud dont les contraintes sont le temps de mise en service et le besoin d’exprimer les besoins en services et leur configuration de manière simple et transparente et de permettre la définition de configurations de déploiement adaptées aux besoins de chaque consommateur, comparables à celles offertes par les clouds privés et optimisées pour tirer profit des spécificités de chaque fournisseur de cloud. Dans cette thèse, nous proposons un framework permettant d’exprimer indépendamment de toute solution sous-jacente les besoins en services et en fournisseurs de cloud et de générer efficacement des infrastructures de déploiement extensibles, adaptatives et contrôlables par le consommateur. Cette solution est composée de MANTUS, un outil permettant l’expression des besoins et la génération automatique d’instances, d’ORBITS, des infrastructures de déploiement multi-cloud adaptables dynamiquement grâce aux mécanismes autonomiques offerts par MANTUS.La solution proposée se décline en plusieurs contributions : tout d’abord l’extension d’un framework IaC (Infrastructure as a Code) existant, dédié à la construction de solutions multi-cloud par des mécanismes de tissage, caractéristiques de la programmation par aspects (AOP), permettant ainsi d’injecter et d’extraire des ressources à la demande. Cette extension, expérimentée sur le framework TOSCA a nécessité la proposition du langage TML (Tosca Manipulation Language) permettant de formaliser et de manipuler ces extensions. Les expérimentations effectuées montrent une surcharge acceptable induite par le mécanisme de tissage. La seconde contribution a été de doter le framework IaC TOSCA d’un outil d’expression des besoins et d’un algorithme de matching en terme, d’une part, de nombre et de caractéristiques de fournisseur de cloud -notamment la localisation- et d’autre part en terme de caractéristiques des services proposés par ceux-ci, permettant de trouver la configuration multi-cloud la plus adaptée. La troisième contribution est la définition d’une architecture « template » multi-couche, ORBITS, offrant des mécanismes d’interopérabilité inter-cloud et une vision haut niveau indépendante des clouds sous jacents. Enfin la dernière contribution proposée est la pile de virtualisation U-cloud et les protocoles liée à son déploiement qui permettent de délimiter les zones contrôlables par le consommateur des zones contrôlées par le provider. Cette proposition est basée sur l’utilisation conjointe de la virtualisation imbriquée (Nested Virtualization) et des micro-hyperviseurs réduisant la zone d’attaque (TCB)<br>Cloud Computing represents one of the most important changes in information and communications technology (ICT) of the latest ten years. However, after a decade since its commercial debut, there are still several applications that cloud computing is not able to fully serve. These are the applications that, due to their particularly stringent requirements, must rely simultaneously on multiple Cloud Service Providers (CSPs), rather than only one. Multiple CSPs can in fact offer a better availability, improve QoS, and break the business dependence w.r.t. a single CSP. A cloud infrastructure based on multiple CSPs is called multi-cloud.Despite the benefits of multi-clouds, organisations (i.e developers and operators of IT services) seldom accept the challenge of building applications and crossing multiple CSP domains. In fact, multi-CSP architectures come at the cost of more complex applications and the logic to in terms of architecture and performance optimization.Recently, Multi-cloud client-oriented architectures emerged as important approach to construct multi-cloud applications. It provides cloud consumers a mechanism to allocate resources over multiple CSPs without requiring any cooperation among the CSPs themselves.In particular, Infrastructure as Code-based (IaC-based) represent the reference paradigm when building multi-cloud applications.However, the adoption of IaC in the multi-cloud context us limited by the fact that the cloud consumer cannot easily reuse the infrastructure code across different applications. This is due to two major problems, which we investigate in this manuscript.First, infrastructure are composed of functional (e.g. resources for applications) and non-functional services (e.g. monitoring). Non-functional related code should be shared at most across different applications and cloud consumers. However, this separation between functional and non-functional code is often blurred and, therefore, non-functional code is hard to be shared across them. This enables the possibility of code re-using across different cloud consumers (e.g., their different multi-cloud infrastructures) and static analysis of infrastructure templates. Furthermore, we present a TML (TOSCA Manipulation Language) aspect specification language to dynamically inject “non-functional” services to the virtual multi-cloud infrastructure. Secondly, the multi-cloud paradigm is limited by the “least common denominator” barrier. The cloud consumer can hardly obtain an optimized usage of resources and services through existing IaC frameworks. Despite compatible with different CSPs, those frameworks do not specialize the output according to deployment context.To tackle the “under-specialization” of multi-cloud templates, we introduce a “context-based matching” scheduling algorithm to select the most compelling set of CSPs according to the cloud consumer needs.To validate such contributions, we defined an end-to-end workflow to optimize a multi-cloud infrastructure definition. More precisely, in our model, the cloud consumer initially models the IaC code as an high-level graph of services, leveraging the combination of TML and context-based matching adoption. The output of this workflow is the instantation of such optimized and fully-featured multi-cloud on most suitable CSPs. We implemented Mantus, a multi-cloud compiler, which encapsulates this workflow and we benchmarked this implementation according to different perspectives as scalability and performance

Le réseau d’accès radio (RAN) 5G vise à faire évoluer de nouvelles technologies couvrant l’infrastructure Cloud, les techniques de virtualisation et le réseau défini par logiciel (SDN). Des solutions avancées sont introduites pour répartir les fonctions du réseau d’accès radio entre des emplacements centralisés et distribués (découpage fonctionnel) afin d’améliorer la flexibilité du RAN. Cependant, l’une des préoccupations majeures est d’allouer efficacement les ressources RAN, tout en prenant en compte les exigences hétérogènes des services 5G. Dans cette thèse, nous abordons la problématique du provisionnement des ressources Cloud RAN centré sur l’utilisateur (appelé tranche d’utilisateurs ). Nous adoptons un déploiement flexible du découpage fonctionnel. Notre recherche vise à répondre conjointement aux besoins des utilisateurs finaux, tout en minimisant le coût de déploiement. Pour surmonter la grande complexité impliquée, nous proposons d’abord une nouvelle implémentation d’une architecture Cloud RAN, permettant le déploiement à la demande des ressources, désignée par AgilRAN. Deuxièmement, nous considérons le sous-problème de placement des fonctions de réseau et proposons une nouvelle stratégie de sélection de découpage fonctionnel centrée sur l’utilisateur nommée SPLIT-HPSO. Troisièmement, nous intégrons l’allocation des ressources radio. Pour ce faire, nous proposons une nouvelle heuristique appelée E2E-USA. Dans la quatrième étape, nous envisageons une approche basée sur l’apprentissage en profondeur pour proposer un schéma d’allocation temps réel des tranches d’utilisateurs, appelé DL-USA. Les résultats obtenus prouvent l’efficacité de nos stratégies proposées<br>5G Radio Access Network (RAN) aims to evolve new technologies spanning the Cloud infrastructure, virtualization techniques and Software Defined Network capabilities. Advanced solutions are introduced to split the RAN functions between centralized and distributed locations to improve the RAN flexibility. However, one of the major concerns is to efficiently allocate RAN resources, while supporting heterogeneous 5G service requirements. In this thesis, we address the problematic of the user-centric RAN slice provisioning, within a Cloud RAN infrastructure enabling flexible functional splits. Our research aims to jointly meet the end users’ requirements, while minimizing the deployment cost. The problem is NP-hard. To overcome the great complexity involved, we propose a number of heuristic provisioning strategies and we tackle the problem on four stages. First, we propose a new implementation of a cost efficient C-RAN architecture, enabling on-demand deployment of RAN resources, denoted by AgilRAN. Second, we consider the network function placement sub-problem and propound a new scalable user-centric functional split selection strategy named SPLIT-HPSO. Third, we integrate the radio resource allocation scheme in the functional split selection optimization approach. To do so, we propose a new heuristic based on Swarm Particle Optimization and Dijkstra approaches, so called E2E-USA. In the fourth stage, we consider a deep learning based approach for user-centric RAN Slice Allocation scheme, so called DL-USA, to operate in real-time. The results obtained prove the efficiency of our proposed strategies

This thesis proposes a collaboration framework for the Web of Things based on the concepts of Service-oriented Architecture and integrated with semantic web technologies to offer new possibilities in terms of efficient asset management during operations requiring multi-actor collaboration. The motivation for the project comes from the rise in disasters where effective cross-organisation collaboration can increase the efficiency of critical information dissemination. Organisational boundaries of participants as well as their IT capability and trust issues hinders the deployment of a multi-party collaboration framework, thereby preventing timely dissemination of critical data. In order to tackle some of these issues, this thesis proposes a new collaboration framework consisting of a resource-based data model, resource-oriented access control mechanism and semantic technologies utilising the Semantic Sensor Network Ontology that can be used simultaneously by multiple actors without impacting each other’s networks and thus increase the efficiency of disaster management and relief operations. The generic design of the framework enables future extensions, thus enabling its exploitation across many application domains. The performance of the framework is evaluated in two areas: the capability of the access control mechanism to scale with increasing number of devices, and the capability of the semantic annotation process to increase in efficiency as more information is provided. The results demonstrate that the proposed framework is fit for purpose.

Pour faire face aux enjeux d’une économie mondialisée, aux fluctuations du marché et aux changements de la demande (personnalisation massive, qualité…), les entreprises recourent de plus en plus aux stratégies de collaboration et d’organisation en réseau et adoptent des stratégies orientées « produit/service ». Cette tendance est renforcée par le développement des applications du Web 2.0 (voire 3.0?) et l’adoption d’architectures orientées services permettant d’augmenter l’interopérabilité et l’agilité des systèmes d’information. En outre, les possibilités offertes par le Cloud Computing permet de rendre le déploiement plus flexible. En parallèle, le développement de stratégies industrielles comme le « lean manufacturing » et le 6-Sigmas permet d’améliorer les procédés, l’organisation industrielle elle-même et la qualité des produits. L’objectif de ce travail de recherche est de coupler la vision « industrielle » à la vision « système d’information » traditionnelle pour permettre de mettre en place un modèle de services industriels composables, orchestrables et « gouvernables ». Pour cela, nous proposons de mettre en place une architecxture de gouvernance globale « connectant » les différentes couches du système (métier/industriel, service, plateforme et infrastructure), permettant d’améliorer la gouvernance du système globale (en évitant les incohérences liées à une prise en compte et une optimisation « isolée » des différents facteurs de performance) tant au niveau organisationnel que technologique. Ceci pourrait permettre d’améliorer les performances tant au niveau « métier » que « technologique », augmenter l’agilité du système et supporter plus efficacement les stratégies de collaboration en développant une approche basée sur la sélection / composition / orchestration de services métier industriels<br>Due to the renewed globalised economical environment and the market evolution (mass customization, sustainability requirements…) the call for developing product-service strategy becomes a major stake, leading industrial companies to set collaborative business organizations and develop business services. This trend has been favored by the large-scale IT environment provided by the web 2.0 and by the development of interoperable and rather agile IT technologies based on services leading to SOA-based information systems reorganization. At the same time, lean and six sigma theories have also been used in industries to improve the industrial process itself so that profitability, quality and reputation are increased. As a new economical and technical model, Cloud Computing has generated a tremendous amount of interest and excitement in recent years as it gives a new and useful way to address IT challenges To achieve the primary goals of these technologies, concepts and models, an efficient industrial organization governance method is necessary. We propose a flexible, efficient, low cost monitoring strategy, it can couple the different layers of economic ecosystem (including business strategies, business/industrial/IT services, execution platforms and infrastructure means) it can overcome existing industrial governance architectures’ limits (most of them are rather “fixed” and lack agility, overall perspective governance as they have unilateral perspective), and it could drive the industry towards better practices, improve ability of enterprises to cope with changes from both a technical and an organizational point of view, as well as reinforce external and internal collaborative work of enterprises

En environnement multi-tenant, les réseaux s'appuient sur un ensemble de ressources matérielles partagées pour permettre à des applications isolés de communiquer avec leurs clients. Cette isolation est garantie par un ensemble de mécanismes à la bordure des réseaux: les mêmes serveurs hébergeant les machines virtuelles doivent notamment déterminer le destinataire approprié pour chaque paquet réseau, copier ces derniers entre zones mémoires isolées et supporter les tunnels permettant l'isolation du trafic lors de son transit sur le coeur de réseau. Ces différentes tâches doivent être accomplies avec aussi peu de ressources matérielles que possible, ces dernières étant tout d'abord destinées aux machines virtuelles. Dans un contexte d'intensification de la demande en haute performance sur les réseaux, les acteurs de l'informatique en nuage ont souvent recours à des équipements matériels spécialisés mais inflexibles, leur permettant d'atteindre les performances requises. Néanmoins, dans cette thèse, nous défendons la possibilité d'améliorer les performances significativement sans avoir recours à de tels équipements. Nous prônons, d'une part, une consolidation des fonctions réseaux au niveau de la couche de virtualisation et, d'autre part, une relocalisation de certaines fonctions réseaux hors des machines virtuelles. À cette fin, nous proposons Oko, un commutateur logiciel extensible qui facilite la consolidation des fonctions réseaux dans la couche de virtualisation. Oko étend les mécanismes de l'état de l'art permettant une mise en cache des règles de commutateurs, ceci afin de permettre une exécution des fonctions réseaux sous forme d'extensions au commutateur. De plus, les extensions sont isolées du coeur du commutateur afin d'empêcher des fautes dans les extensions d'impacter le reste du réseau et de faciliter une mise en place rapide et sûre de nouvelles fonctions réseaux. En permettant aux fonctions réseaux de s'exécuter au sein du commutateur logiciel, sans redirections vers des processus distincts, Oko diminue de moitié le coût lié à l'exécution des fonctions réseaux en moyenne. Notre seconde contribution vise à permettre une exécution de certaines fonctions réseaux en amont des machines virtuelles, au sein de la couche de virtualisation. L'exécution de ces fonctions réseaux hors des machines virtuelles permet d'importants gains de performance, mais lèvent des problématiques d'isolation. Nous réutilisons et améliorons la technique utilisé dans Oko pour isoler les fonctions réseaux et l'étendons avec un mécanisme de partage équitable du temps CPU entre les différentes fonctions réseaux relocalisées<br>Multi-tenant networks enable applications from multiple, isolated tenants to communicate over a shared set of underlying hardware resources. The isolation provided by these networks is enforced at the edge: end hosts demultiplex packets to the appropriate virtual machine, copy data across memory isolation boundaries, and encapsulate packets in tunnels to isolate traffic over the datacenter's physical network. Over the last few years, the growing demand for high performance network interfaces has pressured cloud providers to build more efficient multi-tenant networks. While many turn to specialized, hard-to-upgrade hardware devices to achieve high performance, in this thesis, we argue that significant performance improvements are attainable in end-host multi-tenant networks, using commodity hardware. We advocate for a consolidation of network functions on the host and an offload of specific tenant network functions to the host. To that end, we design Oko, an extensible software switch that eases the consolidation of network functions. Oko includes an extended flow caching algorithm to support its runtime extension with limited overhead. Extensions are isolated from the software switch to prevent failures on the path of packets. By avoiding costly redirections to separate processes and virtual machines, Oko halves the running cost of network functions on average. We then design a framework to enable tenants to offload network functions to the host. Executing tenant network functions on the host promises large performance improvements, but raises evident isolation concerns. We extend the technique used in Oko to provide memory isolation and devise a mechanism to fairly share the CPU among offloaded network functions with limited interruptions

En environnement multi-tenant, les réseaux s'appuient sur un ensemble de ressources matérielles partagées pour permettre à des applications isolés de communiquer avec leurs clients. Cette isolation est garantie par un ensemble de mécanismes à la bordure des réseaux: les mêmes serveurs hébergeant les machines virtuelles doivent notamment déterminer le destinataire approprié pour chaque paquet réseau, copier ces derniers entre zones mémoires isolées et supporter les tunnels permettant l'isolation du trafic lors de son transit sur le coeur de réseau. Ces différentes tâches doivent être accomplies avec aussi peu de ressources matérielles que possible, ces dernières étant tout d'abord destinées aux machines virtuelles. Dans un contexte d'intensification de la demande en haute performance sur les réseaux, les acteurs de l'informatique en nuage ont souvent recours à des équipements matériels spécialisés mais inflexibles, leur permettant d'atteindre les performances requises. Néanmoins, dans cette thèse, nous défendons la possibilité d'améliorer les performances significativement sans avoir recours à de tels équipements. Nous prônons, d'une part, une consolidation des fonctions réseaux au niveau de la couche de virtualisation et, d'autre part, une relocalisation de certaines fonctions réseaux hors des machines virtuelles. À cette fin, nous proposons Oko, un commutateur logiciel extensible qui facilite la consolidation des fonctions réseaux dans la couche de virtualisation. Oko étend les mécanismes de l'état de l'art permettant une mise en cache des règles de commutateurs, ceci afin de permettre une exécution des fonctions réseaux sous forme d'extensions au commutateur. De plus, les extensions sont isolées du coeur du commutateur afin d'empêcher des fautes dans les extensions d'impacter le reste du réseau et de faciliter une mise en place rapide et sûre de nouvelles fonctions réseaux. En permettant aux fonctions réseaux de s'exécuter au sein du commutateur logiciel, sans redirections vers des processus distincts, Oko diminue de moitié le coût lié à l'exécution des fonctions réseaux en moyenne. Notre seconde contribution vise à permettre une exécution de certaines fonctions réseaux en amont des machines virtuelles, au sein de la couche de virtualisation. L'exécution de ces fonctions réseaux hors des machines virtuelles permet d'importants gains de performance, mais lèvent des problématiques d'isolation. Nous réutilisons et améliorons la technique utilisé dans Oko pour isoler les fonctions réseaux et l'étendons avec un mécanisme de partage équitable du temps CPU entre les différentes fonctions réseaux relocalisées<br>Multi-tenant networks enable applications from multiple, isolated tenants to communicate over a shared set of underlying hardware resources. The isolation provided by these networks is enforced at the edge: end hosts demultiplex packets to the appropriate virtual machine, copy data across memory isolation boundaries, and encapsulate packets in tunnels to isolate traffic over the datacenter's physical network. Over the last few years, the growing demand for high performance network interfaces has pressured cloud providers to build more efficient multi-tenant networks. While many turn to specialized, hard-to-upgrade hardware devices to achieve high performance, in this thesis, we argue that significant performance improvements are attainable in end-host multi-tenant networks, using commodity hardware. We advocate for a consolidation of network functions on the host and an offload of specific tenant network functions to the host. To that end, we design Oko, an extensible software switch that eases the consolidation of network functions. Oko includes an extended flow caching algorithm to support its runtime extension with limited overhead. Extensions are isolated from the software switch to prevent failures on the path of packets. By avoiding costly redirections to separate processes and virtual machines, Oko halves the running cost of network functions on average. We then design a framework to enable tenants to offload network functions to the host. Executing tenant network functions on the host promises large performance improvements, but raises evident isolation concerns. We extend the technique used in Oko to provide memory isolation and devise a mechanism to fairly share the CPU among offloaded network functions with limited interruptions

碩士<br>國立成功大學<br>製造資訊與系統研究所<br>102<br>A cloud-based architecture for a multi-machine factory manufacturing information management system (Multi-factory Cloud manufacture information system, m-CMIS) is proposed by this study. It contains the following developments: (1) Construction of a multi-factory hybrid cloud architecture: A private cloud provides factory to storage manufacturing information and a public cloud provides an accessible service module. (2) Developing a web and mobile interface for manufacturing information integration and providing engineers to monitor the machine process information anytime and anywhere. (3) Building a wireless network to improve machine production information via a Wi-Fi setup for machines in the factory to increase real-time performance: In the multi-factory hybrid cloud architecture, machine dealers can flexibly access the public cloud to access service modules for the purpose of developing manufacturing information management systems, or they can directly access the m-CMIS system for the purpose of providing manufacturing information in order to support the ability of manufacturers to integrate multi-factory manufacturing information and improve business service. 　　Based on our performance testing and evaluation of system effectiveness, the results showed that the m-CMIS can help improve information integration, information preservation, and can make real-time information feedback easier.

Mestrado de dupla diplomação com a UTFPR - Universidade Tecnológica Federal do Paraná<br>Smart parking systems are becoming a solution to recurring issues as the number of vehicles in traffic rises in major cities, which can be related to vehicle traffic congestion, unnecessary time spent searching for parking spots, and, consequently, environmental issues. The purpose of these systems is to help drivers who are searching for available parking spaces or who want to reserve for a specified period of time, quickly and, if possible, near the desired location. In this context, there are several modules within smart parking systems that may include cyber-physical systems, multi-agent systems, dynamic pricing and artificial intelligence. This dissertation presents the development of a smart parking system architecture, using Cloud-based technology to integrate a multiagent system into a scalable, decentralized, adaptable and safe environment. The proposed architecture was tested using, as a case study, a web system developed for the management and analysis of smart parking lots, as well as an application for mobile devices, which allows users to interact with multiple functionalities available in this system. Results obtained demonstrate that the implementation of the proposed architecture offers an efficient communication between users who use parking resources and the multi-agent system responsible for the autonomy and intelligence of the parking system.<br>Os sistemas inteligentes de estacionamento estão se tornando uma solução para problemas recorrentes à medida que aumenta o número de veículos em trânsito nas grandes cidades, os quais podem estar relacionados ao congestionamento no tráfego de veículos, tempo desnecessário gasto na busca por vagas e, consequentemente, questões ambientais. O objetivo desses sistemas é auxiliar os motoristas que buscam por vagas disponíveis ou que desejam reservar por determinado período de tempo, de forma rápida e, se possível, próximo ao local desejado. Neste contexto, existem vários módulos dentro dos sistemas inteligentes de estacionamento que podem incluir sistemas ciberfísicos, sistemas multi-agentes, precificação dinâmica e inteligência artificial. Esta dissertação apresenta o desenvolvimento de uma arquitetura para sistemas inteligentes de estacionamento, utilizando tecnologia baseada em Nuvem para integrar um sistema multi-agentes em um ambiente escalável, descentralizado, adaptável e seguro. A arquitetura proposta foi testada utilizando, como um caso de estudo, um sistema web desenvolvido para gestão e análise de estacionamentos inteligentes, bem como uma aplicação para dispositivos móveis, que permite ao usuário interagir com as múltiplas funcionalidades disponibilizadas neste sistema. Resultados obtidos demonstram que a implementação da arquitetura proposta oferece uma comunicação eficiente entre usuários que utilizam os recursos e o sistema multi-agentes responsável pela autonomia e inteligência de um sistema de estacionamento.

碩士<br>國立成功大學<br>製造資訊與系統研究所<br>103<br>Nowadays, if a manufacturer wants to monitor machines or establish a cloud service, they must establish a server room which costs a lot of money. In this study, an architecture for server tenanting called Multi-tenant Cloud Virtual Server Platform (MCVSP) based on an infrastructure as a service (IaaS) is proposed. By using this architecture, a machine provider can provide cloud services to manufacturers. Four items of the MCVSP are: (1) a cloud virtual server service is established to provide manufacturers tenanting cloud virtual servers; (2) a tenant website is established to allow manufacturers to apply a virtual server; (3) a mechanism for recommended virtual server’s specifications according to the number of engineers and machines, (4) a multi-tenant database center is established which saves data for manufactures to isolate. By using MCVSP, manufacturers can tenant servers to reduce the costs on maintaining servers and suppliers can get more benefits from selling machines.

abstract: Nowadays, Computing is so pervasive that it has become indeed the 5th utility (after water, electricity, gas, telephony) as Leonard Kleinrock once envisioned. Evolved from utility computing, cloud computing has emerged as a computing infrastructure that enables rapid delivery of computing resources as a utility in a dynamically scalable, virtualized manner. However, the current industrial cloud computing implementations promote segregation among different cloud providers, which leads to user lockdown because of prohibitive migration cost. On the other hand, Service-Orented Computing (SOC) including service-oriented architecture (SOA) and Web Services (WS) promote standardization and openness with its enabling standards and communication protocols. This thesis proposes a Service-Oriented Cloud Computing Architecture by combining the best attributes of the two paradigms to promote an open, interoperable environment for cloud computing development. Mutil-tenancy SaaS applicantions built on top of SOCCA have more flexibility and are not locked down by a certain platform. Tenants residing on a multi-tenant application appear to be the sole owner of the application and not aware of the existence of others. A multi-tenant SaaS application accommodates each tenant’s unique requirements by allowing tenant-level customization. A complex SaaS application that supports hundreds, even thousands of tenants could have hundreds of customization points with each of them providing multiple options, and this could result in a huge number of ways to customize the application. This dissertation also proposes innovative customization approaches, which studies similar tenants’ customization choices and each individual users behaviors, then provides guided semi-automated customization process for the future tenants. A semi-automated customization process could enable tenants to quickly implement the customization that best suits their business needs.<br>Dissertation/Thesis<br>Doctoral Dissertation Computer Science 2016

M.Sc. (Computer Science)<br>General machine intelligence represents the principal ambition of artificial intelligence research: creating machines that readily adapt to their environment. Machine learning represents the driving force of adaptation in artificial intelligence. However, two pertinent dilemmas emerge from research into machine learning. Firstly, how do intelligent agents learn effectively in real-world environments, in which randomness, perceptual aliasing and dynamics complicate learning algorithms? Secondly, how can intelligent agents exchange knowledge and learn from one another without introducing mathematical anomalies that might impede on the effectiveness of the applied learning algorithms? In a robotic search and rescue scenario, for example, the control system of each robot must learn from its surroundings in a fast-changing and unpredictable environment while at the same time sharing its learned information with others. In well-understood problems, an intelligent agent that is capable of solving task-specific problems will suffice. The challenge behind complex environments comes from fact that agents must solve arbitrary problems (Kaelbling et al. 1996; Ryan 2008). General problem-solving abilities are hence necessary for intelligent agents in complex environments, such as robotic applications. Although specialized machine learning techniques and cognitive hierarchical planning and learning may be a suitable solution for general problem-solving, such techniques have not been extensively explored in the context of cooperative multi-agent learning. In particular, to the knowledge of the author, no cognitive architecture has been designed which can support knowledge-sharing or self-organisation in cooperative multi-agent learning systems. It is therefore social learning in real-world applications that forms the basis of the research presented in this dissertation. This research aims to develop a distributed cognitive architecture for cooperative multi-agent learning in complex environments. The proposed Multi-agent Learning through Distributed Adaptive Contextualization Distributed Cognitive Architecture for Multi-agent Learning (MALDAC) Architecture comprises a self-organising multi-agent system to address the communication constraints that the physical hardware imposes on the system. The individual agents of the system implement their own cognitive learning architecture. The proposed Context-based Adaptive Empathy-deliberation Agent (CAEDA) Architecture investigates the applicability of emotion, ‘consciousness’, embodiment and sociability in cognitive architecture design. Cloud computing is proposed as a method of service delivery for the learning system, in which the MALDAC Architecture governs multiple CAEDA-based agents. An implementation of the proposed architecture is applied to a simulated multi-robot system to best emulate real-world complexities. Analyses indicate favourable results for the cooperative learning capabilities of the proposed MALDAC and CAEDA architectures.

In this dissertation we will propose a solution for a trustable and privacy-enhanced storage architecture based on a multi-cloud approach. The solution provides the necessary support for multi modal on-line searching operation on data that is always maintained encrypted on used cloud-services. We implemented a system prototype, conducting an experimental evaluation. Our results show that the proposal offers security and privacy guarantees, and provides efficient information retrieval capabilities without sacrificing precision and recall properties on the supported search operations. There is a constant increase in the demand of cloud services, particularly cloud-based storage services. These services are currently used by different applications as outsourced storage services, with some interesting advantages. Most personal and mobile applications also offer the user the choice to use the cloud to store their data, transparently and sometimes without entire user awareness and privacy-conditions, to overcome local storage limitations. Companies might also find that it is cheaper to outsource databases and keyvalue stores, instead of relying on storage solutions in private data-centers. This raises the concern about data privacy guarantees and data leakage danger. A cloud system administrator can easily access unprotected data and she/he could also forge, modify or delete data, violating privacy, integrity, availability and authenticity conditions. A possible solution to solve those problems would be to encrypt and add authenticity and integrity proofs in all data, before being sent to the cloud, and decrypting and verifying authenticity or integrity on data downloads. However this solution can be used only for backup purposes or when big data is not involved, and might not be very practical for online searching requirements over large amounts of cloud stored data that must be searched, accessed and retrieved in a dynamic way. Those solutions also impose high-latency and high amount of cloud inbound/outbound traffic, increasing the operational costs. Moreover, in the case of mobile or embedded devices, the power, computation and communication constraints cannot be ignored, since indexing, encrypting/decrypting and signing/verifying all data will be computationally expensive. To overcome the previous drawbacks, in this dissertation we propose a solution for a trustable and privacy-enhanced storage architecture based on a multi-cloud approach, providing privacy-enhanced, dependable and searchable support. Our solution provides the necessary support for dependable cloud storage and multi modal on-line searching operations over always-encrypted data in a cloud-of-clouds. We implemented a system prototype, conducting an experimental evaluation of the proposed solution, involving the use of conventional storage clouds, as well as, a high-speed in-memory cloud-storage backend. Our results show that the proposal offers the required dependability properties and privacy guarantees, providing efficient information retrieval capabilities without sacrificing precision and recall properties in the supported indexing and search operations.