中国邮电高校学报(英文) ›› 2010, Vol. 17 ›› Issue (4): 88-93.doi: 10.1016/S1005-8885(09)60493-3

• Others • 上一篇    下一篇

WPANFIS: combine fuzzy neural network with multiresolution for network traffic prediction

李锐,陈建亚,刘韵洁,王振凯   

  1. 北京邮电大学
  • 收稿日期:2009-06-29 修回日期:2010-01-22 出版日期:2010-08-30 发布日期:2010-08-31
  • 通讯作者: 李锐 E-mail:lirui816@gmail.com
  • 基金资助:

    This work was supported by the National Basic Research Program of China (2007CB310701), Research Fund for University Doctor Subject (20070013013), and Chinese Universities Scientific Fund (2009RC0124).

WPANFIS: combine fuzzy neural network with multiresolution for network traffic prediction

LI Rui, CHEN Jian-ya, LIU Yun-jie, WANG Zhen-kai   

  1. School of Information and Telecommunication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2009-06-29 Revised:2010-01-22 Online:2010-08-30 Published:2010-08-31
  • Supported by:

    This work was supported by the National Basic Research Program of China (2007CB310701), Research Fund for University Doctor Subject (20070013013), and Chinese Universities Scientific Fund (2009RC0124).

摘要:

A novel methodology for prediction of network traffic, WPANFIS, which relies on wavelet packet transform (WPT) for multi-resolution analysis and adaptive neuro-fuzzy inference system (ANFIS) is proposed in this article. The widespread existence of self-similarity in network traffic has been demonstrated in earlier studies, which exhibits both long range dependence (LRD) and short range dependence (SRD). Also, it has been shown that wavelet decomposition is an effective tool for LRD decorrelation. The new method uses WPT as extension of wavelet transform which can decoorrelate LRD and make more precisely partition in the high-frequency section of the original traffic. Then ANFIS which can extract useful information from the original traffic is implemented in this study for better prediction performance of each decomposed non-stationary wavelet coefficients. Simulation results show that the proposed WPANFIS can achieve high prediction accuracy in real network traffic environment.

关键词:

network traffic, prediction, WPT, ANFIS

Abstract:

A novel methodology for prediction of network traffic, WPANFIS, which relies on wavelet packet transform (WPT) for multi-resolution analysis and adaptive neuro-fuzzy inference system (ANFIS) is proposed in this article. The widespread existence of self-similarity in network traffic has been demonstrated in earlier studies, which exhibits both long range dependence (LRD) and short range dependence (SRD). Also, it has been shown that wavelet decomposition is an effective tool for LRD decorrelation. The new method uses WPT as extension of wavelet transform which can decoorrelate LRD and make more precisely partition in the high-frequency section of the original traffic. Then ANFIS which can extract useful information from the original traffic is implemented in this study for better prediction performance of each decomposed non-stationary wavelet coefficients. Simulation results show that the proposed WPANFIS can achieve high prediction accuracy in real network traffic environment.

Key words:

network traffic, prediction, WPT, ANFIS