LEO Satellite Network Traffic Forecasting based on ARIMA-BPNN Model
Chi Han, Wei Xiong, Ronghuan Yu, Jingyu Fu · 2023
Satellite network traffic forecasting provides key information for routing and resource allocation, which is important for the efficient operation of satellite network. However, due to the self-similarity and long-range dependence (LRD) of satellite network traffic, traditional linear or non-linear network traffic forecasting models cannot achieve sufficient forecasting accuracy. A combined model of satellite network traffic forecasting based on BPNN and ARIMA is proposed. BPNN is adopted to forecast the residuals. EMD-ARIMA and BPNN forecasting results are combined to achieve satellite network traffic forecasting. Experimental results on the satellite network traffic data generated by the ON/OFF model show that forecast accuracy of the proposed method is better than traditional model, which verifies the effectiveness of the proposed satellite network traffic forecast model.