TCP兼容二项拥塞控制方案的比较研究

K. Chandrayana, B. Sikdar, S. Kalyanaraman
{"title":"TCP兼容二项拥塞控制方案的比较研究","authors":"K. Chandrayana, B. Sikdar, S. Kalyanaraman","doi":"10.1109/HPSR.2002.1024240","DOIUrl":null,"url":null,"abstract":"Current TCP implementations employ additive increase multiplicative decrease (AIMD) as the congestion control mechanism. Previously, a new set of schemes called binomial congestion control schemes (BCCS) were proposed and a section of these schemes is TCP compliant. In this paper we evaluate the performance of these TCP compliant binomial schemes and show through simulations that AIMD performs better than the other BCCS policies in a wide range networking environments. Specifically, we study the performance of these schemes with respect to throughput, fairness, losses, timeouts and self-similarity. We show that the superior performance of AIMD can be attributed to its more conservative attitude in the presence of losses when it reduces its transmission rate much faster than the other schemes. This results in smaller congestion periods thereby reducing the losses and timeouts which in turn increases the throughput and decreases the degree of self-similarity of the traffic. We also evaluated the performance of TCP Compatible BCCS when they compete with TCP flows. It was found that with sufficiently large number of flows, BCCS competes fairly with TCP. However, with a smaller number of flows in the network TCP flows get a smaller share of the bottleneck and disproportionately higher losses and timeouts.","PeriodicalId":180090,"journal":{"name":"Workshop on High Performance Switching and Routing, Merging Optical and IP Technologie","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2002-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Comparative study of TCP compatible binomial congestion control schemes\",\"authors\":\"K. Chandrayana, B. Sikdar, S. Kalyanaraman\",\"doi\":\"10.1109/HPSR.2002.1024240\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Current TCP implementations employ additive increase multiplicative decrease (AIMD) as the congestion control mechanism. Previously, a new set of schemes called binomial congestion control schemes (BCCS) were proposed and a section of these schemes is TCP compliant. In this paper we evaluate the performance of these TCP compliant binomial schemes and show through simulations that AIMD performs better than the other BCCS policies in a wide range networking environments. Specifically, we study the performance of these schemes with respect to throughput, fairness, losses, timeouts and self-similarity. We show that the superior performance of AIMD can be attributed to its more conservative attitude in the presence of losses when it reduces its transmission rate much faster than the other schemes. This results in smaller congestion periods thereby reducing the losses and timeouts which in turn increases the throughput and decreases the degree of self-similarity of the traffic. We also evaluated the performance of TCP Compatible BCCS when they compete with TCP flows. It was found that with sufficiently large number of flows, BCCS competes fairly with TCP. However, with a smaller number of flows in the network TCP flows get a smaller share of the bottleneck and disproportionately higher losses and timeouts.\",\"PeriodicalId\":180090,\"journal\":{\"name\":\"Workshop on High Performance Switching and Routing, Merging Optical and IP Technologie\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2002-11-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Workshop on High Performance Switching and Routing, Merging Optical and IP Technologie\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/HPSR.2002.1024240\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Workshop on High Performance Switching and Routing, Merging Optical and IP Technologie","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/HPSR.2002.1024240","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7

摘要

当前TCP实现采用AIMD (additive increase multiply reduction)作为拥塞控制机制。在此之前,提出了一组新的方案,称为二项拥塞控制方案(BCCS),其中一部分是TCP兼容的。在本文中,我们评估了这些符合TCP的二项式方案的性能,并通过仿真表明,AIMD在广泛的网络环境中比其他BCCS策略表现得更好。具体来说,我们研究了这些方案在吞吐量、公平性、损失、超时和自相似性方面的性能。我们发现AIMD的优越性能可以归因于它在存在损耗时的保守态度,当它降低传输速率时比其他方案快得多。这导致更小的拥塞周期,从而减少损失和超时,从而增加吞吐量并降低流量的自相似性程度。我们还评估了TCP兼容BCCS与TCP流竞争时的性能。研究发现,在流量足够大的情况下,BCCS可以与TCP进行公平竞争。然而,随着网络中流量数量的减少,TCP流在瓶颈中所占的份额会更小,损失和超时也会不成比例地增加。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Comparative study of TCP compatible binomial congestion control schemes
Current TCP implementations employ additive increase multiplicative decrease (AIMD) as the congestion control mechanism. Previously, a new set of schemes called binomial congestion control schemes (BCCS) were proposed and a section of these schemes is TCP compliant. In this paper we evaluate the performance of these TCP compliant binomial schemes and show through simulations that AIMD performs better than the other BCCS policies in a wide range networking environments. Specifically, we study the performance of these schemes with respect to throughput, fairness, losses, timeouts and self-similarity. We show that the superior performance of AIMD can be attributed to its more conservative attitude in the presence of losses when it reduces its transmission rate much faster than the other schemes. This results in smaller congestion periods thereby reducing the losses and timeouts which in turn increases the throughput and decreases the degree of self-similarity of the traffic. We also evaluated the performance of TCP Compatible BCCS when they compete with TCP flows. It was found that with sufficiently large number of flows, BCCS competes fairly with TCP. However, with a smaller number of flows in the network TCP flows get a smaller share of the bottleneck and disproportionately higher losses and timeouts.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
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