期刊文献+

基于分数Langevin方程的通信量模型及其应用

Parameter Analysis in VoIP with Traffics Multiplexing Scheme Utilizing a New Self-similar Model
在线阅读 下载PDF
导出
摘要 建立了一个考虑QoS和多流复用的通信量模型。模型中的通信量由大量有相同源和目的地址的,独立同分布的数据流汇聚而成,其中每个数据流又由许多独立的符合Pareto分布的ON/OFF支流构成。文章首先分析了支流构成的数据流的概率分布,然后分析得到了数据流复用后的流速的概率分布,接着结合分数Langevin运动方程,得到了一个流量计算公式,该公式属于扩展的分数布朗运动。通过引入分数Langevin运动方程可以将外部影响因子,内部影响因子和Hurst参数有机地联系起来,给通信量的单分形和多重分形一个清晰合理的物理解释。最后使用该模型分析了VoIP中多流复用后的QoS参数,得到了几个重要结论。 In this paper our goal is to design a traffic model that can be used in routers or by network administrators to assist in network design and management.The traffic in the model is the multiplexing of a large number of flows and Qos.The individual flow is composed of a lot of ON/OFF streams.In particular,here the ON/OFF streams being dealt with using probability distribution are different from the ON/OFF sources being superposed in some other papers.The model is flow-based and improved FBM(expanding Fractional Brownian Motion).The ON/OFF streams 's sojourn time accord with Pareto distribution.We take the traffic flows rate as a stochastic variable and deduce the probability distribution of it.Then we take it as a physical variable and think of it's acceleration.Utilizing the fractal Langevin motion equation we get a novel formula for computing the amount of traffic.It is improved FBM.The fractal Langevin motion equation gives a distinct and reasonable physical explanation for traffic trace.The explanation relates the Pareto parameters,external environment impact factors,with Hurst parameter.Finally,the parameter analysis of QoS after the the multiplexing of a large number of flows of VoIP are analyzed.Then we draw some important conclutions.
出处 《计算机工程与应用》 CSCD 北大核心 2004年第30期160-163,196,共5页 Computer Engineering and Applications
基金 国家863信息技术领域重大专项项目基金(编号:2002AA103051 2003AA103510)资助
关键词 自相似 分数Langevin运动方程 流量计算 QoS参数分析 self-similar model,fractal Langevin motion equation,computing the amount of traffic,parameter analysis of QoS
  • 相关文献

参考文献9

  • 1W Leland Taqqu M,W Willinger et al. On the self-similar nature of Ethernet Traffic(Extended Version)[J].IEEE/ACM Transaction on Networking, 1994;12( 1 ): 1~15
  • 2M Garrett,W Willinger. Analysis , Modeling and Generation of SelfSimilar and VBR Video Traffic[C].In:Proceedings of 1994 ACM Sigmetrics Conference ,London ,UK, 1994:160~169
  • 3V Paxson,S Floyd. Wide Area Traffic :The Failure of Poisson Modeling[J].IEEE/ACM Transaction on Networking, 1995; 3 (3)
  • 4M Crovella,A Bestavros.Self Similarity in World Wide Web Traffic:Evidence and Possible Causes[C].In:Proceedings of 1996 ACM Sigmetrics Conference,Philadelphia,PA, 1996:160~169
  • 5M Garrett, W Willinger. Analysis, Modeling and Generation of SelfSimilar and VBR Video Traffic[C].In:Proceedings of 1994 ACM Sigmetrics Conference, London, UK, 1994:160~169
  • 6Jacques L V,R Riedi.Fractional Brownian motion and data traffic modeling:the other end of the spectrum.http:∥citeseer, nj.nec.com/
  • 7I Norros.On the use of FBM in the theory of connectionless networks[J].IEEE Journal on Selected Areas in Commun, 1995;13(6):1028~1038
  • 8WilliamStallings 齐望东 译.高速网络TCP/IP和ATM的设计原理[M].北京:电子工业出版社,1999..
  • 9Anestis K,Dimitrios H.Network Heavy Traffic Modeling Using AlphaStable Self-Similar Process[J].IEEE TRANSACTIONS ON COMMU NICATIONS ,2001 ;49(7): 1203~1215

共引文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部