Electric vehicle charging load space-time distribution prediction method based on graph neural network

The invention relates to an electric vehicle charging load spatial-temporal distribution prediction method based on a graph neural network, and the method comprises the steps: obtaining historical load data and weather data of an electric vehicle in a region where a to-be-predicted point is located, and carrying out the dimension reduction of the weather data; obtaining feature data based on the weather forecast data after dimension reduction processing and historical load data of the electric vehicle; and substituting the feature data after dimension reduction into the trained graph neural network model to obtain electric vehicle charging load space-time distribution. The electric vehicle charging load space-time distribution prediction method realizes electric vehicle charging load space-time distribution prediction, can obtain the charging load potential distribution condition in a city, and compared with an existing deep neural network prediction algorithm, the charging load space-time prediction method p