«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:

期数:

2013年04期

页码:

20-23

栏目:

智能、算法、系统工程

出版日期:

1900-01-01

文章信息/Info

Title:

Research on an Improved Prediction Model of Network Traffic

文章编号:

1673-629X（2013）04-0020-04

作者:

赵伟

江苏自动化研究所

Author(s):

ZHAO Wei

关键词:

网络流量; 预测模型; 长相关; 短相关; 经验模式分解

Keywords:

network traffic; prediction model; long-range dependence; short-range dependence; empirical mode decomposition

文献标志码:

A

摘要:

网络流量预测是网络优化研究中的热点,由于网络流量的自相似性导致了网络流量的长相关特性,现有的网络流量预测模型无法对其进行准确预测,且时间复杂度高,为了提高网络流量预测的准确性和效率,文中提出了一种改进的网络流量预测模型.首先,基于经验模式分解对长相关的网络流量进行预处理,并证明了它们是短相关的,然后通过AIC准则和逆函数法来建立模型进行流量预测.仿真结果表明,该模型的预测效果较好,不但降低了算法的复杂度,而且预测精度高于传统的方法

Abstract:

Network traffic prediction is the hot spot in the network optimization,however,the self-similarity feature of network traffic has led to the nature of long-range dependence,the existing network traffic prediction model can not accurately forecast the network traffic, and has high complexity. In order to improve the accuracy and efficiency of the network traffic prediction,present an improved network traffic prediction model. Firstly,the long-range traffic is preprocessed based on the empirical mode decomposition,and proved that the preprocessed traffic is short-range dependence. Then,the prediction model is established by the AIC criterion and the inverse function method to predict traffic. The simulation results show that the performance of the model is better,not only reduces the complexity of the method,and the prediction accuracy is higher than the traditional methods

常用功能

更新日期/Last Update: 1900-01-01