Short Term Prediction of Electric Vehicle Charging Load Based on Optimized Genetic Algorithm

With the continuous attention and promotion of electric vehicles, governments of electric vehicles have made great progress. However, due to the randomness and unpredictable nature of electric vehicle charging, it will have a certain impact on the power system. To effectively predict the charging load of electric vehicles can effectively alleviate the impact of electric vehicle charging on the distribution network to a certain extent. This paper proposes a method to predict the charging load of electric vehicles by using the genetic algorithm to optimize the numerical value and weight threshold of the number of the hidden layer units of the neural network structure, and compares it with the BP neural network prediction method. The experimental data show that the prediction method has higher prediction accuracy.