Research on Network Traffic Forecasting Model Based on GCN-LSTM

Network traffic prediction is of great significance for optimizing network resource allocation, improving network service quality and ensuring network security. Traditional forecasting methods, such as autoregressive moving average model (ARIMA) and support vector machine (SVM), have many limitations when dealing with complex network traffic data. Although the deep learning method can improve the prediction accuracy to a certain extent, it is still insufficient to mine the temporal and spatial correlation of network traffic. In this paper, a network traffic prediction model based on graph convolution neural network (GCN) is proposed. This model captures the spatial correlation between network nodes by constructing graph structure, and combines with long-term and short-term memory network (LSTM) to process time series data, thus realizing efficient prediction of network traffic. The experimental results show that the proposed model is superior to the traditional methods in prediction accuracy and stability.