Towards the development of residential smart districts: The role of EVs

Nowadays, the transition to a more sustainable energy and transport system is necessary. Smart City and districts, through the integration of technologies such as Renewable Energy Sources (RES) and Electric Vehicles (EVs) represent the future of the urban landscape. This work faces this theme at a district level, considering a residential neighborhood of a big metropolitan area and proposing a model for the development of a Smart Residential District, including RES, loads and EVs. The optimum quantities of installed RES power are calculated through an optimization procedure based on an Artificial Neural Network. In particular, a predictive model based on feed-forward neural network trained with Levenberg-Marquardt back-propagation learning algorithm is proposed to forecast solar irradiation and load power consumption. This enables to optimize the self-consumption of electricity produced from renewable sources using EVs batteries, to limit the electrical power exchanged with the grid and the related carbon dioxide emissions.