Traffic Load Prediction of Power Communication Network Based on Graph Neural Network

With the rapid growth of power communication network traffic, accurate analysis and management of power communication network traffic has become a key factor to ensure the safe, stable and efficient power communication network. However, the traditional forecasting method cannot investigate the traffic of upstream and downstream nodes, which affects the prediction and analysis of the overall network. Therefore, this paper proposes a traffic prediction model based on Graph Neural Network (GNN). We analyzed the topology architecture of Power Communication Network, and designed and optimized the GNN forecast model to predict network traffic information. The network link traffic occupancy is divided into several levels for prediction. After experimental testing, the prediction results of this model have high accuracy and reliability, which is of great significance to the stability research of power communication network.