一种基于小波变换和FIR神经网络的广域网网络流量预测模型

该文提出了一种基于小波变换和FIR神经网络的广域网网络流量预测模型，首先采用小波分解把网络流量数据分解成小波系数和尺度系数，即高频系数和低频系数，将这些不同频率成分的系数单支重构为高频流量分量和低频流量分量，利用FIR神经网络对这些分量分别进行预测，将合成之后的结果作为原始网络流量的预测。实验结果表明:采用该模型对实际的广域网网络流量数据进行预测，不仅可以得到较快的收敛效果，而且预测性能比现有的小波神经网络和FIR神经网络要好得多。

A WAN Network Traffic Prediction Model Based on Wavelet Transform and FIR Neural Networks

In this paper, a WAN network traffic prediction model based on wavelet transform and FIR neural networks is proposed. The model employs wavelet transform which decomposes the traffic into high frequency coefficients and low frequency coefficients , then these different frequency coefficients are reconstructed by single branch to the high frequency traffic parts and the low frequency traffic parts which are sent individually into different FIR neural networks for prediction. The synthesized outputs are the predicted results of the original network traffic. The experimental results with the real WAN network traffic show that the proposed model has much better prediction performance compared to the wavelet neural networks and the FIR neural networks.