A centralized state of charge estimation technique for electric vehicles equipped with lithium-ion batteries in smart grid environment

Electric vehicles (EVs) not only act as a load in grid-to-vehicle but also as a storage system in vehicle-to-grid concept. Further, both renewable energy sources (RESs) and EVs can be classified under multi-distributed generations. In this regard, fossil-based power generation units as traditional back-ups or distributed generations can be replaced by a combination of renewable energy sources (RESs) and EVs to alleviate suffering from the fluctuation of renewable power generation units. However, successful coordination of electric vehicles and renewable energy systems require accurate state estimations of EVs such as state of charge (SoC) due to intermittent renewable energy output. Hence this combination emphasizes the need for an efficient method of SoC estimation. Since battery management system is in the initial stage of development, none of the proposed intelligent state of charge estimation techniques has been capable of being implemented in battery management system. In this regard, the present article proposes an off-board real-time state of charge estimation technique, can be implemented in fog computing architecture, for lithium-ion battery based on the National Aeronautics and Space Administration (NASA) database enabling to compare the outcome of the present article with the recent studies. In this article, a non-dominated sorting genetic algorithm II (NSGA-II) is combined with an artificial neural network (ANN) technique to estimate SoC of four batteries simultaneously. The results of the proposed technique indicate high convergence rate and high accurate estimation.