Base station intelligent control method based on heterogeneous graph neural network flow prediction

The invention discloses a base station intelligent control method based on heterogeneous graph neural network flow prediction, comprising the following steps: setting a Pearson's correlation coefficient threshold, and collecting flow data of each base station for continuous N days; calculating a first Pearson's correlation coefficient between every two base stations every day according to the flow data of the base stations every day, and constructing an isomorphic graph based on the first Pearson's correlation coefficients; constructing a base station heterogeneous graph based on the isomorphic graph, and dividing the base station heterogeneous graph into a training set and a test set; constructing a neural network model comprising a graph convolutional network and a full-connection network, and training the neural network model by using the training set and the test set to obtain a traffic prediction model; predicting the flow of the 5G base station by using the flow prediction model, and controlling the on-