Optimal management of parking lots as a big data for electric vehicles using internet of things and Long-Short term Memory

In recent years, many people have been moving to urban life. It has been estimated that more than 60% of the population will live in urban environments in 2030. Some systems that can face the challenges of increasing population will help develop the smart city. Today, the relationship between various urban systems, such as transportation, communication and business networks, is very complicated. These complexities have greatly enhanced the importance of intelligent and quick coordination of cities with modern technologies. Internet of Things (IoT) one of the new technologies in the present era, and its application in cities can be considered as a major innovation for sustainable urban development. A smart city is a city that has the ability to effectively provide and present data in a meaningful way. On the other hand, today, with the expansion of the influence of Electric Vehicles (EV) in the transportation industry and the need for these EV to charge their battery, it is impossible to ignore the impact of these EV on the smart grid. In this thesis, the presence of EV in the context of urban and IoT is examined. As we use the intelligent city and the IoT, the historical data can be collected from the behavior of the owners of EV and the Deep learning method, one of the methods of machine learning; can be used to predict the level of charging of EV when entering the parking lot, EV location and parking lot connection periods. This will make us more successful in optimizing energy management, which is designed to minimize operational costs. The proposed model has been implemented on the IEEE 33-bus distribution system to evaluate the performance of the proposed optimization method for scheduling of distribution network in the presence of EV in the GAMS software environment. The results showed that the net profit is increased under the proposed plan.