期刊文献+

基于SDN的胖树数据中心网络多路径负载均衡算法研究 被引量:9

RESEARCH ON SDN-BASED MULTI-PATH LOAD BALANCING ALGORITHM OF FAT-TREE DATACENTER NETWORK
下载PDF
导出
摘要 软件定义网络SDN(Software Defined Network)通过将网络设备的控制层与数据层分离解耦,能够实现网络的集中控制和流量的灵活转发,因此被广泛应用于数据中心等相关领域。在数据中心网络中,为了提高网络的带宽和吞吐量,多采用具有多路径特性的层次型网络拓扑结构,如胖树拓扑结构。然而传统路由算法对多路径的支持非常有限,无法充分利用网络剩余带宽。重点研究基于SDN的胖树数据中心网络多路径负载均衡算法。利用SDN网络集中控制的特点,获取多路径实时状态信息,计算各路径当前可用带宽,根据数据流的带宽需求选择最佳转发路径。实验结果表明,该算法无论在降低网络传播时延还是在提高网络吞吐量等方面都优于传统路由算法,能够实现胖树数据中心网络的多路径负载均衡。 Software Defined Networking( SDN) is widely used in datacenters and other related fields to achieve centralized control of the network and flexible traffic forwarding by decoupling the control plane from the data plane. To improve the network bandwidth and throughput,datacenter network employ layering network topology structure with multi-path characteristics,such as Fat-tree. However,traditional routing algorithms have limited support for multi-path routing,they cannot make full use of the remaining bandwidth of the network. Therefore,this paper mainly studies the SDN based multi-path load balancing algorithm of Fat-tree datacenter network. By using the centralized control of SDN network,obtain multi-path real-time status information; calculate the available bandwidth of each path,and selects the best forwarding route according to the bandwidth requirement of the data stream. The experimental results show that the proposed algorithm is superior to traditional routing algorithms in not only reducing network propagation delay but improving network throughput,thus it is capable to achieve multi-path load balancing in Fat-tree datacenter networks.
出处 《计算机应用与软件》 2017年第9期147-152,共6页 Computer Applications and Software
基金 安徽省自然科学基金项目(1408085MF125)
关键词 软件定义网络 SDN 胖树 数据中心网络 多路径负载均衡 Software defined network SDN Fat tree Datacenter network Multi-path load balancing
  • 相关文献

参考文献2

二级参考文献41

  • 1Wang Qingbo. Virtuulizul inn and (loud Computing (il Chinese). Publishing House of lIelmlic ludustry, Oer. 2009.
  • 2AIla Kuut, Data ilkI r-volutiou tutorial 011 state of the mi. issuel. and lhlIele. COlplIl,- Vdor, HlI.53 IlU. 17. PI. 2939-2965. Dec. 2009.
  • 3Altrt Crn u lkrg. JaIlHs l hnuilron, David A. Malz. ParVPtn Patel. The 01 of a (Ioud n-scuuh prohhIS il data t-e-nte-r networks. ACM 5ICCO,IAi Computer PIJlIlJit-nlion Htl jIV, vol. 39. 110.1. PI 68-73. 2009.
  • 4Ciso IC . Data ,lIltr Loud 1lCJlmlil data ceruer services. Solution Hp(pl-l1Ij Nt-ntl, Ul.if,I.I. Mar. 2004.
  • 5Ciseo Ttthlwal Heport Nt TrtlHls Antl the Au-hiter-ture or Dahl Ctltr Ntl-r (il ChilD. 2008.
  • 6Cil1l I.hoa NVlIcn. Mnlia e- d Cheriet. Malhitu Lemny. Vidor Htij. Andrew hltk.Jr1. Alin Palrala. EnvirolWnlil-aware virtual data center network. ClItlIN Netw ork. vo1.56. 10.2538-2550. July 2012.
  • 7I-liroki ShiraYUlclgi, Hiroshi Yamada, KtlIji kono. Honeyguide A VM Migru-lion-Aware Nt-lwork Topology for Saving EIltrgy Consumprion il Data Center Networks, in 1tE SYI[l1I Oil Commnrr? m(I COlI1rlIlflIS (ISU. 2012), Ip.460-467. July 2012.
  • 8Xiaoqiuo Mg, Vasileio POIS, Li ZI,ng, lroving the Slalaloly (Or Data Center Networks with TrufTil-uWal Virtual MUthine Plufmtnl, Sun Difgu. in INfOCOMIO, pp.I-9. Mar. 2010.
  • 9Mohanl,1l1 Hajjar, Xi Sun, Yu-Wti Iri Su Duvid lvIalz, 5anjuy Huu, Kun-wudee SripanidkuldlUi, Mohit Tnwurmnlani , (fCloldwurd Round Planning for Brlal Migralion or flerpri,p Aplin,liol 1( Ihe Cloud, in tiu- ACM S,I .1 tnn-n-st CIVIl OJl )11 CJlJlJI1JlitliJ11 51COMM lO),New 1)lhi, 11.243-254, Aug. 2010.
  • 10M. AI-Fa, A. Loukissns, and A. Vahdat, A SeultJc, Commodity Datu CI-ler Network Ard,ilelurl in ilI A(M SfJculnIPfP.sl Grol(l on 1)11 Connnu-Ir, ilCCOMM 08). 5 . 11, 11.63-74. A I. 2008.

共引文献6

同被引文献53

引证文献9

二级引证文献28

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