Competitive FIFO Buffer Management for Weighted Packets

Fei Li
{"title":"Competitive FIFO Buffer Management for Weighted Packets","authors":"Fei Li","doi":"10.1109/CNSR.2009.28","DOIUrl":null,"url":null,"abstract":"Motivated by providing differentiated services on the Internet, we consider efficient online algorithms for buffer management in network switches. We study a FIFO buffering model, in which unit-length packets arrive in an online manner and each packet is associated with a value (weight) representing its priority. The order of the packets being sent should comply with the order of their arriving time. The buffer size is finite. At most one packet can be sent in each time step. Our objective is to maximize weighted throughput, defined by the total value of the packets sent. In this paper, we design competitive online FIFO buffering algorithms, where competitive ratios are used to measure online algorithms' performance against the worst-case scenarios. We first provide an online algorithm with a constant competitive ratio 2. Then, we study the experimental performance of our algorithm on real Internet packet traces and compare it with all other known FIFO online competitive algorithms. We conclude that for the same instance, the algorithms' experimental performances could be different from their competitive ratios; other factors such as packet flow characteristics and buffer sizes affect the outcome. Our algorithm outperforms other online algorithms when the buffer resource is limited.","PeriodicalId":103090,"journal":{"name":"2009 Seventh Annual Communication Networks and Services Research Conference","volume":"59 5 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 Seventh Annual Communication Networks and Services Research Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CNSR.2009.28","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4

Abstract

Motivated by providing differentiated services on the Internet, we consider efficient online algorithms for buffer management in network switches. We study a FIFO buffering model, in which unit-length packets arrive in an online manner and each packet is associated with a value (weight) representing its priority. The order of the packets being sent should comply with the order of their arriving time. The buffer size is finite. At most one packet can be sent in each time step. Our objective is to maximize weighted throughput, defined by the total value of the packets sent. In this paper, we design competitive online FIFO buffering algorithms, where competitive ratios are used to measure online algorithms' performance against the worst-case scenarios. We first provide an online algorithm with a constant competitive ratio 2. Then, we study the experimental performance of our algorithm on real Internet packet traces and compare it with all other known FIFO online competitive algorithms. We conclude that for the same instance, the algorithms' experimental performances could be different from their competitive ratios; other factors such as packet flow characteristics and buffer sizes affect the outcome. Our algorithm outperforms other online algorithms when the buffer resource is limited.
加权数据包的竞争性FIFO缓冲管理
为了在互联网上提供差异化的服务,我们考虑了网络交换机中有效的在线缓冲管理算法。我们研究了一个FIFO缓冲模型,其中单位长度的数据包以在线方式到达,每个数据包都与代表其优先级的值(权重)相关联。发送数据包的顺序应与到达时间的顺序一致。缓冲区大小是有限的。每个时间步长最多只能发送一个报文。我们的目标是最大化加权吞吐量,由发送的数据包的总价值定义。在本文中,我们设计了竞争性在线FIFO缓冲算法,其中竞争性比率用于衡量在线算法在最坏情况下的性能。我们首先提供了一个具有恒定竞争比2的在线算法。然后,我们研究了该算法在真实互联网数据包跟踪上的实验性能,并将其与所有其他已知的FIFO在线竞争算法进行了比较。我们得出结论,对于相同的实例,算法的实验性能可能不同于它们的竞争比率;其他因素,如数据包流特性和缓冲区大小也会影响结果。当缓冲区资源有限时,我们的算法优于其他在线算法。
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:604180095
Book学术官方微信