一种网络流量预测的小波神经网络模型

结合小波变换和人工神经网络的优势，建立一种网络流量预测的小波神经网络模型。首先对流量时间序列进行小波分解，得到小波变换尺度系数序列和小波系数序列，以系数序列和原来的流量时间序列分别作为模型的输入和输出，构造人工神经网络并且加以训练。用实际网络流量对该模型进行验证，结果表明，该模型具有较高的预测效果。

A wavelet neural network model of network traffic forecast

Integrating the merit of wavelet transform with that of artificial neural network, a wavelet neural network (WNN ) model for forecasting network traffic was created. First, the traffic time series were decomposed to the scaling coefficient series and wavelet coefficient series. Taking the coefficient series as input while original time traffic series as output, an artificial neural network was established and trained. The simulation results on real network traffic show that WNN model is more successful than traditonal methods in network traffic prediction.