Network Traffic Prediction by Traffic Decomposition

Abstract

For the complicated characteristic of network traffic, a prediction algorithm based on traffic decomposition is introduced in this paper. The complex correlation structure of the network history traffic is decomposed according to different protocols and then predicted with wavelet method separately. For the traffic series under different protocols and different time scale, self-similarity is analyzed and different prediction model is selected for predicting. The result series is reconstructed with wavelet method. Simulation results show that the combination method can achieve higher prediction accuracy rather than that without traffic decomposition.