A Method of Network Traffic Analysis Based on Multiple-Combination Model

The traditional stationary network traffic model (ARIMA) is incapable of describing non-stationary characteristics. In the process of predicting, the accuracy will weaken with the increase of step. As a non-stationary network traffic model, NN (neural network) could make up for the defect of stationary model, which can not describe the non-stationary qualities of the network traffic. However, the parameters choice of NN doesn’t have a specific theoretical foundation. According to the problems above, the paper proposes a method of multiple combinations. First, we compared the errors of ARIMA with those of Elman model, and then designed a multiple-combination model which applied to network traffic analysis. The result shows that the method is superior to a single model.