Design of a Novel Variable Bit Rate Video Traffic Prediction Model Based on Neural Networks

Abstract

The video business has gradually become the main business of the network traffic, video traffic is Variable Bit Rate (VBR), which has nonlinear and sudden features, a single prediction model is not fit for describing those features, and prediction accuracy is not high. Because of wavelet analysis has advantages of multi-resolution and dealing with unexpectedness, and the neural network has better nonlinear fitting characteristics, in order to improve the prediction performance, the paper researched on the problem of VBR video traffic prediction based on neural networks, a novel prediction model AMWM is proposed, the model firstly introducing BP neural network to multi-fractal wavelet model, and designing prediction method, which introduced multi-fractal wavelet model to model VBR video traffic, and then applying BP neural network to forecast scale coefficient decomposed, and forecast multiplier using AR model, and predict traffic generated by wavelet reconstruction. Finally, the model is built and simulated. The experimental result shows that prediction performance based AMWM is better compared with multi-fractal wavelet model.