Electric vehicle charging load prediction method based on user behaviors

The invention provides an electric vehicle charging load prediction method based on user behaviors, and the method comprises the following steps: A, obtaining data, including vehicle data, time data, position data, trajectory data, POI data and SOC data of an electric vehicle user; b, preprocessing the data; c, mining travel data of the electric vehicle, including map matching, regeneration data generation, spatial modeling through grid division, POI recognition and functional area space-time flow feature mining; and D, based on a data mining result in the step C, performing travel process simulation and charging decision simulation of the electric vehicle user, and based on the travel process simulation and the charging decision simulation, calculating a charging demand of the user to obtain a theoretical charging demand of each region. According to the invention, the actual demand of the user is more fully analyzed and mined based on the real behavior data of the electric vehicle user, and the charging load