小波消噪和神经网络的网络流量混沌预测

网络流量数据中含有大量噪声，对网络流量预测精度产生不利影响，为此，提出一种小波消噪和神经网络相融合的网络流量混沌预测模型。采用小波技术对网络流量数据进行消噪处理，采用关联维数确定BP神经网络输入变量个数，采用BP神经网络建立网络流量预测模型。结果表明，与消噪前比，小波消噪和神经网络模型更能准确刻画网络流量的变化趋势，有效提高了网络流量的预测精度，为非线性预测问题提供了一种新的研究思路。

Chaotic prediction for network traffic flow based on wavelet de-noising and neural network

The network traffic data contain a lot of noise,and they have negative effect on the network traffic prediction accuracy,therefore,this paper proposes network flow prediction model based on wavelet de-noising and neural network.The network traffic data are de-noised by wavelet.The input number of BP neural network is determined by correlation dimension.The BP neural network is used to establish the prediction model of network traffic flow.The results show that,compared with the model which doesn’t carry out de-noising,the proposed model can more accurately describe the change of the network traffic trends,so as to effectively improve the prediction accuracy of network traffic.It provides a new research idea for the nonlinear prediction problem.