Balancing Energy, Redundancy, and Performance in Datacenter Networks

Antonio Araujo, L. Sampaio, A. Ziviani
{"title":"Balancing Energy, Redundancy, and Performance in Datacenter Networks","authors":"Antonio Araujo, L. Sampaio, A. Ziviani","doi":"10.1109/SBRC.2015.24","DOIUrl":null,"url":null,"abstract":"The current large-scale datacenters typically adopt redundancy of servers and communication devices for increased reliability and availability. A highly redundant infrastructure, however, is one of the challenges of the area due to the high energy consumption. This paper presents BEEP, an energy-efficient strategy for datacenter networks based on the Fat Tree topology. Our strategy uses multipaths and the global view offered by software-defined networks to balance the energy efficiency, the equipment redundancy level, and the performance gain when dealing with the traffic demands. BEEP was implemented in an OpenFlow network and the multipaths were implemented using MPTCP (Multipath TCP). The experimental results in variants of the Fat Tree topology show gains in the energy efficiency with the strategy in the order of 30% to 45%, in addition to a better utilization of the available bandwidth, as more alternative paths are available.","PeriodicalId":307266,"journal":{"name":"2015 XXXIII Brazilian Symposium on Computer Networks and Distributed Systems","volume":"110 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 XXXIII Brazilian Symposium on Computer Networks and Distributed Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SBRC.2015.24","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

Abstract

The current large-scale datacenters typically adopt redundancy of servers and communication devices for increased reliability and availability. A highly redundant infrastructure, however, is one of the challenges of the area due to the high energy consumption. This paper presents BEEP, an energy-efficient strategy for datacenter networks based on the Fat Tree topology. Our strategy uses multipaths and the global view offered by software-defined networks to balance the energy efficiency, the equipment redundancy level, and the performance gain when dealing with the traffic demands. BEEP was implemented in an OpenFlow network and the multipaths were implemented using MPTCP (Multipath TCP). The experimental results in variants of the Fat Tree topology show gains in the energy efficiency with the strategy in the order of 30% to 45%, in addition to a better utilization of the available bandwidth, as more alternative paths are available.
平衡数据中心网络的能量、冗余和性能
当前的大型数据中心通常采用服务器和通信设备的冗余,以提高可靠性和可用性。然而,由于高能耗,高度冗余的基础设施是该地区面临的挑战之一。提出了一种基于胖树拓扑结构的数据中心网络节能策略BEEP。我们的策略使用多路径和软件定义网络提供的全局视图,在处理流量需求时平衡能源效率、设备冗余级别和性能增益。BEEP在OpenFlow网络中实现,多路径使用MPTCP (Multipath TCP)实现。Fat Tree拓扑变体的实验结果表明,除了更好地利用可用带宽外,该策略的能源效率提高了30%至45%,因为有更多的可选路径可用。
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