基于主成分分析与BP神经网络的网络流量预测  

Network flow prediction based on principal component analysis and BP neural network

作　　者：刘英华[1] 

机构地区：[1]华中农业大学楚天学院,武汉430205

出　　处：《激光杂志》2015年第6期151-153,157,共4页Laser Journal

基　　金：2012年湖北省高校省级教学研究项目(2012458);2014华中农业大学校级科研项目(K201405)

摘　　要：为了提高网络流量的预测精度,提出了一种主成分分析与BP神经网络的网络流量预测模型(PCA-BPNN)。首先采用相空间重构网络流量学习样本,并采用主成分分析选择网络流量的输入向量,降低输入向量的维数,然后将学习样本输入到BP神经网进行训练,建立网络流量预测模型,实验结果表明,相对于当前经典网络流量预测模型,PCA-BPNN提高了网络流量的预测精度,具有广泛的应用前景。In order to improve the prediction accuracy of network flow,this paper puts forward a network traffic prediction model based on principal component analysis and BP neural network. Firstly,phase space reconstruction is used to obtain the learning sample of network flow,and principal component analysis is used to extract the input vector to reduce the dimension of the input vector,and then the learning samples are input to the BP neural network to train and establish of network traffic prediction model,finally the simulation experiment is used to test the performance of model. The results show that,compared to the classical models of network traffic,the proposed model improves the prediction accuracy of network traffic and has widely application.

关 键 词：神经网络 预测模型 网络流量 主成分分析 

分 类 号：TP393.06[自动化与计算机技术—计算机应用技术] TP183[自动化与计算机技术—计算机科学与技术]