Self-Similar Property for TCP Traffic under the Bottleneck Restrainment

T. Nakashima, T. Sueyoshi
{"title":"Self-Similar Property for TCP Traffic under the Bottleneck Restrainment","authors":"T. Nakashima, T. Sueyoshi","doi":"10.1109/AINAW.2007.324","DOIUrl":null,"url":null,"abstract":"The scale-invariant burstiness or self-similarity has been found in real network and has been subject to the file size of Web servers or the duration of user sessions. In addition, self-similar burstiness has been characterized by the transport layer protocol. Traffic dynamics, however, are mainly generated by physical conditions such as the resource restrainment. In this paper, we have investigated self-similar property for TCP traffic under the resource restrainment to make the network parameter vary using the network simulator. After analyzing the simulated results, following properties were extracted. Firstly, self-similar traffic rather than exponential traffic generates the performance gain especially in the throughput, while the bottleneck bandwidth restrainment under the condition at exceeding 4% packet loss rate eliminates the performance gain. Secondly, on the saturated condition with nearly no packet loss caused by the increase of client number, the self-similar property is sustained with the Hurst parameter with the value of 0.5 for all alpha's. Finally, large link delay exceeding 700 msec emphasizes the self-similar property for all alpha's enlarging the Hurst parameter approximately at the value of 0.8.","PeriodicalId":338799,"journal":{"name":"21st International Conference on Advanced Information Networking and Applications Workshops (AINAW'07)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"21st International Conference on Advanced Information Networking and Applications Workshops (AINAW'07)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/AINAW.2007.324","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

Abstract

The scale-invariant burstiness or self-similarity has been found in real network and has been subject to the file size of Web servers or the duration of user sessions. In addition, self-similar burstiness has been characterized by the transport layer protocol. Traffic dynamics, however, are mainly generated by physical conditions such as the resource restrainment. In this paper, we have investigated self-similar property for TCP traffic under the resource restrainment to make the network parameter vary using the network simulator. After analyzing the simulated results, following properties were extracted. Firstly, self-similar traffic rather than exponential traffic generates the performance gain especially in the throughput, while the bottleneck bandwidth restrainment under the condition at exceeding 4% packet loss rate eliminates the performance gain. Secondly, on the saturated condition with nearly no packet loss caused by the increase of client number, the self-similar property is sustained with the Hurst parameter with the value of 0.5 for all alpha's. Finally, large link delay exceeding 700 msec emphasizes the self-similar property for all alpha's enlarging the Hurst parameter approximately at the value of 0.8.
瓶颈约束下TCP流量的自相似特性
在实际网络中已经发现了规模不变的突发性或自相似性,并且受Web服务器的文件大小或用户会话持续时间的影响。此外,传输层协议还对自相似突发性进行了表征。而流量动态主要是由资源约束等物理条件产生的。本文利用网络模拟器研究了TCP流量在资源约束下的自相似特性,使网络参数发生变化。通过对模拟结果的分析,提取了以下属性:首先,自相似流量比指数流量产生性能增益,特别是在吞吐量方面,而在丢包率超过4%的情况下,瓶颈带宽限制消除了性能增益。其次,在客户端数量增加几乎不造成丢包的饱和条件下,所有alpha参数的Hurst值均为0.5,自相似性质保持不变。最后,超过700 msec的大链路延迟强调了所有alpha的自相似性质,将Hurst参数近似地扩大到0.8。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信