Academic literature on the topic 'IOT based Smart parking system'

Air pollution is a global issue which has negative impacts not only on the environment but also on human health. Therefore, it is important to design and implement systems to allow cities and villages to monitor air quality so that they take the required actions to maintain a good air quality in the city/village. Since IoT facilitates implementing efficient monitoring systems, many IoT systems have been proposed to monitor air pollution. In this paper, we review different IoT-based systems to monitor air quality. In addition, we do an experiment where we propose and evaluate our system to monitor air pollution in a smart village, Veberöd, utilizing the LoRaWAN and the IoT platform, Yggio, which is already used in the village. Our proposed system is used to monitor temperature, humidity, pressure, PM1, PM2.5, PM10, CO2, and CO. As a result of our experiment, we found that the data received by Yggio was encoded, and Yggio did not provide the decoding functionality to decode the data sent from our devices. Therefore, another IoT platforms were used to decode, visualize, and analyse the data. The results of the experiments shows that as far as PM1, PM2.5, PM10, and CO are concerned, the air quality in the village is good. The results also showed that some LoRaWAN messages were lost and never received on Yggio.

Nowadays, the installation of residential battery energy storage (BES) has increased as a consequence of the decrease in the cost of batteries. The coupling of small-scale energy generation (residential PV) and residential BES promotes the integration of microgrids (MG), i.e., clusters of local energy sources, energy storages, and customers which are represented as a single controllable entity. The operations between multiple grid-connected MGs and the distribution network can be coordinated by controlling the power exchange; however, in order to achieve this level of coordination, a control and communication MG interface should be developed as an add-on DMS (Distribution Management System) functionality to integrate the MG energy scheduling with the network optimal power flow. This thesis proposes an edge-cloud architecture that is able to integrate the microgrid energy scheduling method with the grid constrained power flow, as well as providing tools for controlling and monitoring edge devices. As a specific case study, we consider the problem of determining the energy scheduling (amount extracted/stored from/in batteries) for each prosumer in a microgrid with a certain global objective (e.g. to make a few energy exchanges as possible with the main grid). The results show that, in order to have better optimization of the BES scheduling, it is necessary to evaluate the composition of a microgrid in such a way as to have balanced deficits and surpluses, which can be performed with Machine Learning (ML) techniques based on past production and consumption data for each prosumer.

Tesis por compendio de publicaciones<br>La presente tesis doctoral presenta el diseño de un sistema de gestión de la información basado en IoT para eficiencia energética en edificios inteligentes. En primer lugar se analizaron las limitaciones y problemas de las propuestas en literatura que abordan la gestión en edificios para su eficiencia energética. Tras este estudio teórico, se propuso un modelo de carácter general en el que se establecen las entradas a considerar en la gestión del edificio para conseguir eficiencia energética, así como las posibles salidas del mismo. La idea de este modelo es la de su instanciación específica en edificios enmarcados en un contexto determinado. De esta forma, por cada contexto son analizadas las entradas con un relevante impacto en el consumo energético, así como las salidas a considerar atendiendo a las características funcionales de dicho contexto. Como parámetros relevantes a considerar durante la gestión del edificio, está la información sobre la localización de los ocupantes. Por esta razón, en esta tesis se implementó un mecanismo de localización en espacios de interior basado en la fusión de datos provenientes de sensores infrarrojos y un sistema RFID encargado de monitorizar a los ocupantes del edificio. La precisión en los resultados alcanzados tras la evaluación de este mecanismo, cubre de manera satisfactoria las necesidades en cuánto a la precisión requerida en los datos de localización a integrar durante la gestión del edificio, proporcionando una precisión media de 1.5 m de error en localización. Resuelta la localización, se desarrolló un mecanismo capaz de predecir las condiciones de confort a proporcionar a los ocupantes atendiendo a las preferencias de estos, a las condiciones medioambientales y al nivel de actividad inferido en el edificio. La tasa de éxito media en la estimación de los parámetros óptimos de confort según las condiciones contextuales del problema fue del 91%. Una vez implementados estos mecanismos, se integró dicha información como entradas del sistema de gestión propuesto para eficiencia energética, y se realizaron experimentos en varios edificios inteligentes tomados como referencia. El objetivo de estos experimentos es la de extraer el impacto de incorporar dicha información en términos del ahorro energético alcanzado. Los resultados demostraron que es posible alcanzar un ahorro energético medio al mes de operación del sistema de gestión del 20%, en comparación con el consumo del mes anterior, durante el cual no se consideró ningún tipo de gestión para eficiencia energética en el edificio. La siguiente extensión del sistema de gestión propuesto consiste en incorporar al propio usuario del sistema en la operación del mismo. El objetivo aquí es el de involucrar al usuario en el ahorro del consumo energético del edificio. Para este objetivo se establecieron diversas estrategias tales como: proporcionar información sobre el consumo energético asociado a la actividad del propio usuario, ofreciendo consejos y recomendaciones a llevar a cabo y dirigidas al ahorro energético, permitiendo al usuario que estableciera sus propias reglas de control en el sistema de gestión, etc. Varios experimentos se llevaron a cabo para evaluar el impacto de esta extensión del sistema. Como resultado de dichos experimentos, pudo comprobarse cómo los usuarios del sistema cambiaron su comportamiento asociado al uso que realizaban de las infraestructuras del edificio. De esta forma, y tras un mes de experimentación, se consiguió incrementar en un 9\% el ahorro hasta ahora conseguido, alcanzando así hasta un 29% de ahorro. Tras alcanzar todos los objetivos planteados al inicio de la presente tesis doctoral, y en vista de los resultados conseguidos, podemos afirmar que ha sido demostrada y validada la aplicabilidad y efectividad del sistema propuesto para la gestión de información basado en IoT para eficiencia energética en edificios inteligentes.<br>This thesis presents an IoT-based design for an information management system to improve energy efficiency in smart buildings. Firstly, a theoretical focus to identify the requirements for improving energy efficiency in buildings, followed by an analysis of the limitations and problems of solutions proposed in the literature for this respect. After this theoretical analysis a general model was proposed in which the inputs and outputs to be considered in the management proposed to improve energy efficiency in buildings were identified. The idea of this model was its instantiation in buildings in a given context. For each context, the inputs representing a relevant energetic impact in buildings are analysed, as the target outputs according to functional characteristics of the building context. Information on the localization of the occupants is an important factor since it permits a more precise management of the building, while satisfying the individual comfort needs of the occupants. This is why we implement a localization mechanism for enclosed spaces based on fusing the data from infrared sensors and an RFID system. The accuracy obtained after evaluation of the mechanism amply covered the requirements as regards the data to be integrated in the building management system with a mean accuracy error of 1.5 m. Having solved the localization problem, we developed a mechanism for predicting the comfort conditions that would be necessary bearing in mind the occupants' preferences, the environmental conditions and the activity level of the building. The mean success rate in estimating the optimal comfort parameters according to contextual conditions was 91%. The above information concerning user localization and preferred comfort conditions served as input for building management system for energy efficiency, and experiments were carried out in several smart reference buildings. The aim was to assess the effect of the introduced information in terms of energy savings. With these inputs and taking the corresponding infrastructure management measures it was possible to achieve a mean energy saving during operation of 20% compared with the previous month's consumption when no such energy efficiency management system was in operation. The next move was to incorporate the users themselves into the operation of the system, in the hope of encouraging further energy saving. Several strategies were adopted in this respect, including providing information on the energy consumed as a result of the individual user's activities, offering recommendations for saving energy and permitting the users to establish their own rules for managing the system. Several experiments in this respect confirmed that users will change their behaviour as regards the use they make of the building's infrastructures. A one month experiment led to a 9\% saving in the energy consumed, rising to 29% in a building with a high degree of monitoring and actuation. Having attained all the objectives set out at the beginning of this thesis and in view of the results, the viability and effectiveness of the proposed system for managing IoT-based information to save energy in smart buildings is demonstrated.

Nous avons travaillé sur l'un des axes de recherche les plus importants de la ville intelligente, à savoir les systèmes de transport intelligents (STI). Les ITS englobent plusieurs domaines, tels que les systèmes de notification électronique des véhicules, les informations sur le trafic, le stationnement intelligent et l'environnement. Cependant, dans cette thèse, nous ciblons deux de ses domaines importants : i) le stationnement intelligent et ii) le trafic routier. Nous avons commencé notre recherche par le cas d'utilisation du stationnement intelligent. En effectuant une revue de la littérature, nous avons réalisé que différentes approches de Machine Learning (ML) et de Deep Learning (DL) ont été utilisées pour des solutions de stationnement intelligent. Dans la plupart de ces approches proposées, les zones de stationnement fermées ont été ciblées avec différents ensembles de caractéristiques pour prédire le "taux d'occupation" dans les zones de stationnement. Cela nous a incités à effectuer une analyse comparative pour répondre aux questions suivantes : compte tenu du cas d'utilisation de la prédiction de stationnement, comment les modèles ML traditionnels se comportent-ils par rapport aux modèles DL complexes ? Avec des données volumineuses, les modèles ML traditionnels moins complexes peuvent-ils surpasser les modèles DL complexes ? Quelle est la performance de ces modèles pour prédire la disponibilité des places de stationnement individuelles dans la rue plutôt que de prédire le taux d'occupation global d'une zone de stationnement fermée. Pour répondre à ces questions, nous avons choisi cinq algorithmes ML classiques bien connus (K-Nearest Neighbours, Random Forest, Decision Tree) et un algorithme DL (Multilayer Perceptron). Pour approfondir notre étude, nous formons un modèle d'apprentissage d'ensemble, dans lequel nous combinons tous les modèles ML et DL susmentionnés. Nous avons utilisé un énorme ensemble de données sur les pa rkings de la ville de Santander, en Espagne, qui comprend environ 25 millions d'enregistrements. Nous proposons également de recommander des places de stationnement disponibles en fonction de l'emplacement actuel du conducteur. En poursuivant nos objectifs de recherche, nous avons effectué une revue de la littérature sur le trafic routier et avons constaté que le trafic routier est souvent associé à la pollution atmosphérique et à la pollution sonore. Cependant, à notre connaissance, la pollution atmosphérique et la pollution sonore n'ont jamais été utilisées dans le problème de la prédiction du trafic. Dans cette partie de notre recherche, nous avons d'abord utilisé la pollution de l'air (CO, NO, NO2, NOx, et O3) avec les variables atmosphériques, telles que la vitesse et la direction du vent, la température et la pression pour améliorer la prévision du trafic dans la ville de Madrid. Cette expérience réussie nous a incités à étendre notre étude à un autre facteur, qui est égalemen t fortement corrélé au trafic routier, à savoir la pollution sonore. Ainsi, dans le prolongement de nos travaux précédents, nous utilisons dans cette partie de notre recherche la pollution sonore pour améliorer la prévision du trafic dans la ville de Madrid<br>We worked on one of the most significant research directions in Smart City, i.e., Intelligent Transportation System (ITS). ITS encapsulates several domains, such as electronic vehicles notification systems, traffic information, smart parking, and environment. However, in this thesis, we target two of its important domains; i) Smart Parking, and ii) Road Traffic. We started our research with Smart Parking use case. Performing literature review, we realized that different Machine Learning (ML) and Deep Learning (DL) approaches have been used for smart parking solutions. In most of these proposed approaches, enclosed parking areas were targeted with different feature sets to predict the "occupancy rate" in parking areas. It inspired us to conduct a comparative analysis to answer following questions; Given the parking prediction use case, how do the traditional ML models perform as compared to complex DL models? Provided big data, can less complex, traditional ML models outperform complex DL models? How well these models can perform to predict the availability of the individual on-street parking spots rather than predicting the overall occupancy rate of an enclosed parking area. To answer these questions, we choose five well-known classical ML algorithms (K-Nearest Neighbours, Random Forest, Decision Tree) and DL algorithm (Multilayer Perceptron). To take our investigation into depth, we train Ensemble Learning Model, in which we combine all the above-mentioned ML and DL models. A huge parking dataset of city of Santander, Spain, has been used which consists of around 25 million records. We also propose to recommend available parking spots based on the current location of the driver. Moving forward with our research goals, we performed literature review on road traffic and found road traffic associated with air pollution and noise pollution often. However, to the best of our knowledge, air pollution &amp; noise pollution have never been use d in traffic prediction problem. In this part of our research, firstly we used air pollution (CO, NO, NO2, NOx, and O3) along with the atmospheric variables, such as wind speed, wind direction, temperature, and pressure to improve the traffic forecasting in the city of Madrid. This successful experiment motivated us to extend our investigation to another factor, which is also strongly correlated with road traffic i.e., noise pollution. Hence, as an extension of our previous work, in this part of our research, we use noise pollution to improve the traffic prediction in the city of Madrid

In this new digital age, efficiency, quality and competition are all increasing rapidly as companies leverage the Industrial Internet of Things (IIoT). However, while industrial innovation moves at a faster and faster pace, educational institutions have lagged in the development of the curriculum and environment needed to support further development of the IIoT. To fully realize the potential of the IIoT in the manufacturing sector educational institutions must support the technological training and education rigor demanded to instill the skills and thought leadership to move the industry forward. The purpose of this research is to provide an IIoT core system in an educational factory environment. This system will assist in teaching basic principles of IIoT in the factory while simultaneously allowing for students to envision the manufacturing journey of any facility by implementing principles of IIoT. This will be accomplished by providing all the following capabilities together in a single data system: unified connectivity, role-based data display, real-time issue identification, data analytics, and augmented reality.

Dissertação de Mestrado Integrado em Engenharia Mecânica apresentada à Faculdade de Ciências e Tecnologia<br>Hoje em dia, tempo é um dos recursos mais preciosos que as pessoas possuem. Graças à evolução da tecnologia e juntando a revolução da indústria 4.0, vivida no momento, a procura de um lugar de estacionamento livre representa tempo perdido e um desafio para os engenheiros encontrarem uma solução. Problemas como congestionamento de tráfego, poluição do ar, lugares de estacionamento limitados e a segurança nas estradas, são alguns dos desafios mais importantes do século atual. Este projeto propõe um sistema de estacionamento inteligente, implementado em cada um dos lugares dos parques de estacionamento públicos. Composto por um circuito projetado para obter informações em tempo real sobre a disponibilidade de cada lugar e um futuro aplicativo móvel inteligente para o cliente usar e ser capaz de reservar um lugar escolhido.O objetivo do projeto é desenvolver um sistema de estacionamento inteligente que permita reduzir o tráfego, tornando mais fácil encontrar lugares de estacionamento livres, reduzindo assim o risco de distração enquanto procura um lugar ou até mesmo problemas relacionados com questões ambientais. Utilizando um Sistema Cyber-Físico, no qual um mecanismo é controlado e monitorizado por um software, é possível alterar o estado do mecanismo de acordo com a necessidade e contexto. Será possível concretizar a finalidade de bloqueio e desbloqueio de um lugar de estacionamento através de um simples pressionar do botão.A estratégia de desenvolvimento desta pesquisa foi separar o projeto em três sistemas principais. Uma forma bruta de cada subsistema foi alcançada com sucesso. O sistema mecânico criado, usando o software Solidworks, foi feito para corresponder a todos os requisitos encontrados ao longo do projeto. Na plataforma mecânica gerada encontramos todos os componentes do hardware escolhido. Por último, mas não menos importante, o sistema de software foi desenvolvido, onde podemos controlar a plataforma via WI-FI. Todas as etapas mencionadas foram desenvolvidas com sucesso e constituem a fase inicial de um sistema que visa facilitar o processo de encontrar um lugar de estacionamento disponível dentro de um período de tempo limitado.<br>Nowadays, time is one of the most precious resources that people have. Thanks to the evolution of technology and living on the revolution of the industry 4.0, searching for an available parking place represents wasted time and a challenge for the developers to find a solution for it. Problems such as traffic congestion, air pollution, limited parking spaces and safety on the roads are few of the most important challenges of the actual century. This project proposes a smart parking system, implemented on each slot of a parking facility. Composed by a circuit designed to gain real time information regarding availability of the slot and a future smart mobile application for the customer to use and beable to reserve a chosen slot.The purpose of the project is to develop a smart parking system that can reduce traffic by making it easier to find empty parking slots, thus lowering the risk of distracted driving or environmental issues. Using a Cyber-Physical System, in which a mechanism is controlled and monitored by a software, changing the status of the mechanism according with the need and context, it will be possible to concretize the purpose of blocking and unblocking a car slot through a simple press of a button.The strategy of developing this research was to seperate the project in three main systems. One raw shape of each subsystem was successfully achieved. The mechanical system created using Solidworks Software, was meant to correspond to all the requirements expressed alongside the project. On the platform generated we find all the chosen hardware componentes. Last but not least, the software system, where we have been able to control the platform via WI-FI. All the mentioned steps were succefully developed and constitutesthe initial stage of a system that is meant to facilitate the process of finding an available parking slot within a limited period of time.

碩士<br>元智大學<br>資訊管理學系<br>104<br>A procedure is architecture of IOT for smart life, to achieve a intelligent parking system research. My agenda is Introduction、Literature 、Research method、Contribution、Conclusion. Recently there were many outlet-mall opening. How to make business and customers via IOT technology to achieve overall intelligent parking is my research motivation. Although public or private own parking , it use the process was entry 、manual or electronic introduce 、parking and payment for leave . If all those of process add IOT technology that would bond to be more efficient . This researching was use common electric product and basic technology ,there neither need high funds nor team, via a architecture to verification the feasibility of deployment.

Internet of things (IoT) and Artificial Intelligence (AI) both are currently in high demand and have a lot of scope in future as well. Nowadays, the concept of smart cities is very popular. IoT is a key player for achieving the idea of smart cities. Many efforts are being made in this sector of IoT for making a better infrastructure of any city. In urban cities, we are also facing many problems like very less parking facility, safety during travelling and congestion of traffic. As the movement of world is very fast and seamless transportation system is not providing by current transport system. People are getting delay due to extra jam on traffic while they are on their own way to work, home or any other places. This is a major reason of fuel burning and time delay. Currently, almost every person who has a vehicle is facing a very serious problem of parking. With proposed IoT solution we can solve these problems more efficiently. In our thesis, we have come up with an algorithm that can help in resolving traffic congestion and making parking system smarter. We have proposed an algorithm for reading car number plate i.e. License Number Plate (LNP) detection based on advanced algorithm for convergence of grey scale image and morphologic effect. We suggested for traffic control, Intersection time deduction advanced techniques with the help of IoT sensors and AI (Fuzzy system). In given time duration number of passed vehicles can be maximized. We have also included Cloud based parking system with the help of IoT, Which uses IoT based module to scan vacant space in parking area. Hereafter, we can work on AI techniques for Vehicle Over speed monitoring, automatically detecting road accident and contact emergency number, an IoT based system for privacy and security of data for Smart parking and improvement in traffic control.

With the advent of new technologies and growing need of reliable and sophisticated ways to make machine to machine communication, the current concept of Internet has evolved from the traditional human interaction dependent events. Now it is possible to integrate a physical world device into the internet itself, essentially making it a smart object and therefore making it possible for inanimate objects to talk to each other, processing and exchanging data. This new concept is called Internet of Things (IoT). In present day IoT has found widespread application in the domain of Home Automation, Health Care, Productive Business, Logistics, Smart Cities, Intelligent Transportation etc. In this work, an Intelligent Lighting System is developed which incorporates the concepts of IoT Home Automation. System comprises of a Gateway Node for Internet connectivity and master control, Wireless LED Nodes having high power LED, microcontroller, LED driver, wireless module and power supply, and Wireless Sensor Nodes. This system allows an end user to search for wireless LED nodes nearby, pair them and remotely perform ON/OFF and brightness control of LED lights. It also incorporates an Intrusion detection system which turns on the lights in a room upon motion detection. The system also captures usage data of the LEDs and user can retrieve and view usage statistics in graphical form. Just the use of power efficient lights are not enough to effectively reduce overall electricity consumption bill, it can be greatly optimized by using a Smart Lighting System. It allows the user to calibrate when exactly a light should be on and at what brightness. Also it can make life more simple allowing full remote control over all the lights in the building. It can also detect intruders via the use of motion sensors and various other sensors can be used to add more features. Capturing usable data from the system can open ways for better optimization arrangements. Raspberry Pi has been used as the Gateway Node and master control for the system. It also hosts the local webserver and database server and is connected to the Zigbee coordinator. With Arduino as the secondary controller and CAT4101 as the driver IC, and Zigbee as the wireless router, the LED node turns ON/OFF and adjusts brightness according to the command sent from ix raspberry pi. It also sends acknowledgement signals back to master control so that records are updated in the database. Wireless Sensor node sends motion detection signal to master control and accordingly master control sends command to turn on lights in the room. End user connects to the server as a client using an Android App and from there the LEDs can be controlled and usage data can be retrieved. Client pings the Server via php and Server sends respond in JSON format.