Electric vehicle charging and discharging scheduling strategy based on dynamic electricity price

The rapid growth in the number of electric vehicles (EVs) has significantly increased the demand for electricity for residents. In addition, because the charging time of EVs highly coincides with the peak period of user electricity consumption, the disorderly charging of EVs will lead to the overload of the power grid transformer. Traditional control methods lack certain robustness and do not fully consider the uncertainty of EVs. As a result, the V2G participation rate of electric vehicles cannot be determined, and the control reliability is low. To solve the above problems, this paper designs a reinforcement learning framework of Long Short-Term Memory network and Improved Linear programming algorithm (LSTM-ILP) to control the V2G of EVs.This paper comprehensively considers the overall electric vehicle charging demand, discharge potential, large grid electricity price, aggregator, and users' interests demands. Firstly, aiming to minimize the charging and discharging fee of EVs and the load peak-to-valley difference of the power grid, a dynamic electricity price based on Long Short-Term Memory neural network (LSTM) is established. Then, the improved linear programming algorithm (ILP) is used to solve the charging and discharging optimization problem of EV, and the results are fed back to the input of the next iterative update of the LSTM, and finally, the optimal electricity price and EV charging and discharging schedule are achieved. The simulation results show that the LSTM-ILP framework can not only reduce the charging fee of electric vehicles, but also achieve the Peak and valley trimming of the grid load. Charging costs for EV users were reduced by 42.1% compared with unordered charging, and by 22% percent compared with orderly charging.