混沌理论与极限学习机的网络流量预测  

Forecasting of Network Traffic Based on Chaos Theory and WA-ELM

作　　者：张芹[1] ZHANG Qin(School of Computer Information Management, Inner Mongolia University of Finance and Economics, Hohhot 010051,China)

机构地区：[1]内蒙古财经大学计算机信息管理学院,内蒙古呼和浩特010051

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2016年第5期636-638,644,共4页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：国家社会科学基金资助项目(BCA060016);内蒙古自然科学基金资助项目(2013MS0901)

摘　　要：提出一种混沌理论和极限学习机的网络流量预测模型.首先对网络流量时间序列进行小波分解得到不同分量,然后采用混沌理论对各分量进行相空间重构,并利用神经网络中的极限学习机进行建模,得到各分量的预测结果,最后采用对分量的预测值进行叠加组合,并采用具体网络流数据集进行模拟测试.相对于其他模型,混沌理论和极限学习机的网络流量预测模型能准确地反映网络流量的变化特性,获得更高精度的预测结果.Aiming at chaotic characteristics of network traffic and the shortage of traditional forecasting models,to improve forecasting accuracy of network traffic,a new network traffic prediction model based on chaos theory and extreme learning machine is proposed.Firstly,wavelet analysis is used to decompose the network traffic and different frequency characteristics are obtained,and secondly,phase space reconstruction of components is carried out by chaos theory,lastly,wavelet analysis is used to get the final results of network traffic.The results show that the compared with other models,the proposed model can accurately reflect the chaotic characteristics of the network traffic,and obtain the higher accuracy of the prediction results.

关 键 词：网络流量 极限学习机 小波分析 相空间重构 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]