Electric vehicle charging load clustering and load forecasting based on long short term memory neural network

With the increasing number of electric vehicles, the charging load of electric vehicles has a huge impact on the scheduling and operation of the grid. Therefore, the charging load forecasting of the electric vehicle population has important significance to the safety and stability of the grid. This paper proposes an electric vehicle load forecasting model based on fuzzy C-means and long short term memory neural network. Firstly, the daily loads of electric vehicles are clustered by fuzzy C-means to obtain different daily load types. Then, this paper selects the factors affecting the load as input characteristics, such as temperature, precipitation. Neural network parameters of different load types are trained, and all types of loads are predicted. Next, predicted loads of various types are added to the total forecast load. Finally, the method of this article is verified by using the actual data of a certain place. The results show that the accuracy of the forecasting methods mentioned in this paper is relatively high.