Electric Vehicle Load Prediction Method Based on Back-Propagation Neural Network

Abstract The development of large-scale electric vehicles puts forward new requirements for safe and reliable operation of distribution network. Accurate and reliable EV load forecasting can effectively support large-scale EV load grid-connected operation and provide conditions for reasonable regulation of demand side resources. Firstly, this paper analyses the necessity and feasibility of electric vehicle load forecasting from the scale characteristics, regulation ability and informatization level of electric vehicle development. Then, a load forecasting method based on Back-Propagation neural network algorithm is proposed. Finally, the applicability of the model was verified based on the daily load of electric vehicles. The results show that the model can realize the effective load prediction of electric vehicles, and will support the smooth progress of related work.