计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (3): 101-103.DOI: 10.3778/j.issn.1002-8331.2009.03.029

• 网络、通信、安全 • 上一篇    下一篇

自相似业务量产生机理与模型精度分析

陈炳锋1,徐从富1,何 俊2   

  1. 1.浙江大学 计算机学院,杭州 310027
    2.浙江省辐射环境监测站,杭州 310012
  • 收稿日期:2008-07-08 修回日期:2008-09-27 出版日期:2009-01-21 发布日期:2009-01-21
  • 通讯作者: 陈炳锋

Analysis on generation mechanism of self-similar traffic and its accuracy of model

CHEN Bing-feng1,XU Cong-fu1,HE Jun2   

  1. 1.College of Computer Science,Zhejiang University,Hangzhou 310027,China
    2.Radiation Environment Monitoring Station of Zhejiang Province,Hangzhou 310012,China
  • Received:2008-07-08 Revised:2008-09-27 Online:2009-01-21 Published:2009-01-21
  • Contact: CHEN Bing-feng

摘要: 对通过叠加满足Pareto重尾分布的ON/OFF业务点产生自相似业务量的方法进行了较系统的分析。在介绍了这种自相似业务量实现方式的理论基础后,给出了一种检验业务点叠加数量与模型精度之间关系的研究方法。仿真结果表明:当叠加ON/OFF业务点数量为44时,自相似业务量Hurst参数的相对平均误差分别为6.8%(H=0.6)和5.0%(H=0.9);当叠加ON/OFF业务点数量为132时,自相似业务量Hurst参数的相对平均误差为1.25%(H=0.6)和0.85%(H=0.9)。

关键词: 自相似, 重尾分布, Pareto, ON/OFF

Abstract: In this paper,the self-similar traffic generated by multiplexing the ON/OFF points which meet the Pareto heavy-tail distribution is discussed.The corresponding theory of the method above is introduced and then the research method on the relationship of the number of the points and the precision of the self-similar traffic model is given.Simulation results show that the relative average error of the Hurst parameter in the self-similar model is 6.8% when H=0.6 and 5.0% when H=0.9 in the case that the number of ON/OFF points is 44.While corresponding data change to 1.25% when H=0.6 and 0.85% when H=0.9 respectively in the case that the number of ON/OFF points reach to 132.

Key words: self-similar, heavy-tail distribution, Pareto, ON/OFF