Charging Load Forecasting of Electric Vehicle Based on Monte Carlo and Deep Learning

An intelligent charging load forecasting method of the electric vehicle plays a vital role in power generation and power market optimization. In this paper, electric vehicles have been categorized as electric buses, electric taxis, electric private cars and electric buses. The probabilistic models of load influencing factors are investigated, and then the calculation models of charging power for different types of electric vehicles have been attained. According to the predicted results of electric vehicle ownership, the charging load of the electric vehicle is calculated by use of Monte Carlo Simulation method for extraction of both electric vehicle initial charging state and charging time. Finally, a deep learning algorithm LSTM (Long Short Term Memory) has been utilized to predict the charging load of electric vehicles. The effectiveness of the proposed method is illustrated by the simulation results.