基于SDN架构的高性能网络拥塞避免策略

J4 ›› 2016, Vol. 38 ›› Issue (01): 1-10.

• 论文 • 下一篇

基于SDN架构的高性能网络拥塞避免策略

柴燕涛，董德尊，张鹤颖，朱成阳，廖湘科

（国防科学技术大学计算机学院,湖南长沙 410073）

收稿日期:2015-08-17 修回日期:2015-10-13 出版日期:2016-01-25 发布日期:2016-01-25
基金资助:
国家自然科学基金（61272482）；国家863计划（2013AA01A208）

A high performance network congestion
avoidance protocol based on SDN architecture

CHAI Yantao，DONG Dezun，ZHANG Heying，ZHU Chengyang，LIAO Xiangke

（College of Computer,National University of Defense Technology,Changsha 410073,China）

Received:2015-08-17 Revised:2015-10-13 Online:2016-01-25 Published:2016-01-25

摘要/Abstract

摘要：

拥塞管理是高性能网络领域的重要研究方向，网络拥塞会对网络的全局性能产生较大影响。现有的拥塞管理多采用分布式拥塞避免策略，能够在一定程度上解决网络的拥塞问题，但其处理过程基于局部信息，不能充分利用网络资源，处理效率偏低。近期，人们提出软件定义网络（SDN）架构，该架构采用集中控制器和多层网络技术，能够较好地获取网络的全局信息。在原有工作的基础上提出了一种基于SDN架构的全局拥塞避免策略OSCP，该策略在拥塞信息获取和控制信息的传输上，改进了原有的解决方案，并结合自适应传输进行网络路由。实验结果表明，该策略可以较好地避免和解决网络中存在的拥塞问题，降低网络延迟并提高饱和吞吐率。

关键词: 拥塞避免, SDN, 多层网络, 资源分类, 热点

Abstract:

In the field of high performance networks, congestion management is an important research problem and has great influence on the global performance. Traditional congestion management protocols usually use distributed congestion control mechanism to alleviate the network congestion. But since this way of processing bases on local information only, it cannot make full use of network resources. Recently, the architecture of software defined network (SDN) has been proposed, and it adopts a centralized controller and the multilayer network technique, making it possible to get the global information of networks. So in this paper, we put forward a high performance network congestion avoidance protocol, called overall situation congestion protocol (OSCP), which is based on the SDN architecture. The protocol improves the existing congestion avoidance protocols on congestion information acquisition and the transmission of control information, and it integrates adaptive transmission to perform network routing. Experimental results show that the proposed protocol can effectively prevent and solve network congestion problem, reduce the network latency, and increase the throughput.

Key words: congestion avoidance;SDN;multi-layer network;resource classification;hot-spots

柴燕涛，董德尊，张鹤颖，朱成阳，廖湘科. 基于SDN架构的高性能网络拥塞避免策略[J]. J4, 2016, 38(01): 1-10.

CHAI Yantao，DONG Dezun，ZHANG Heying，ZHU Chengyang，LIAO Xiangke. A high performance network congestion
avoidance protocol based on SDN architecture [J]. J4, 2016, 38(01): 1-10.

参考文献［15］

［1］	Michelogiannakis G,Jiang N,Becker D,et al. Channel reservation protocol for oversubscribed channels and destinations［C］∥Proc of International Conference on High Performance Computing,Networking,Storage and Analysis,2013:52.
［2］	Benson T,Anand A,Akella A,et al. Understanding data center traffic characteristics［J］. ACM SIGCOMM Computer Communication Review,2010,40(1):9299.
［3］	Hamada T, Nakasato N. Infiniband trade association. Infiniband architecture specification,volume 1,release 1.2.1［EB/OL］.［20150312］.http://www.infinibandta.com.
［4］	Yang C Q,Reddy A V S. A taxonomy for congestion control algorithms in packet switching networks［J］. Network,IEEE,1995,9(4):3445.
［5］	Ramakrishnan K, Floyd S, Black D. The addition of explicit congestion notification (ecn) to IP:IETF RFC 3168［S］.NewYork: Network Working Group, IETF, 2001.
［6］	Ferrer J L, Baydal E,Robles A,et al. Congestion management in mins through marked and validated packets［C］∥Proc of the 15th Euromicro International Conference on Parallel,Distributed and NetworkBased Processing,2007:254261.
［7］	Gran E G,Eimot M, Reinemo S A,et al. First experiences with congestion control in Infiniband hardware［C］∥Proc of 2010 IEEE International Symposium on Parallel Distributed Processing,2010:112.
［8］	Santos J R,Turner Y,Janakiraman G. Endtoend congestion control for Infiniband［C］∥Proc of the 22nd Annual Joint Conference of the IEEE Computer and Communications,2003:11231133.
［9］	Ferrer J L,Baydal E,Robles A,et al. On the influence of the packet marking and injection control schemes in congestion management for mins［C］∥Proc of the 14th International EuroPar Conference on Parallel Processing,2008:930939.
［10］	Pfister G,Gusat M,Denzel W,et al. Solving hot spot contention using Infiniband architecture congestion control［C］∥Proc of HPIPC’05,2005:1.
［11］	Peh L S,Dally W J. Flitreservation flow control［C］∥Proc of the 6th International Symposium on High Performance Computer Architecture, 2000:7384.
［12］	Song Y H,Pinkston T M. Distributed resolution of network congestion and potential deadlock using reservationbased scheduling［J］. IEEE Transactions on Parallel and Distributed Systems,2005,16(8):686701.
［13］	Duato J,Johnson I,Flich J,et al. A new scalable and costeffective congestion management strategy for lossless multistage interconnection networks［C］∥Proc of the 11th International Symposium on HighPerformance Computer Architecture,2005:108119.
［14］	Banerjee A,Moore S W. Flowaware allocation for onchip networks［C］∥Proc of the 2009 3rd ACM/IEEE International Symposium on NetworksonChip,2009:183192.
［15］	AlFares M,Loukissas A,Vahdat A. A scalable,commodity data center network architecture［J］. ACM SIGCOMM Computer Communication Review,2008,38(4):6374.

[1]	柴燕涛，董德尊，张鹤颖，朱成阳，廖湘科. 基于SDN架构的高性能网络拥塞避免策略[J]. J4, 20160101, 38(01): 1-10.
[2]	白坚镜, 顾瑞春, 刘清河. SDN环境中基于Bi-LSTM的DDoS攻击检测方案[J]. 计算机工程与科学, 2023, 45(02): 277-285.
[3]	陈俊彦, 李玥, 梁楚欣, 雷晓春. SDN多控制器部署及流量均衡研究[J]. 计算机工程与科学, 2021, 43(05): 830-835.
[4]	樊自甫，张丹，李书. 基于软件定义网络的数据中心网络负载均衡算法研究[J]. 计算机工程与科学, 2018, 40(06): 1017-1022.
[5]	刘培磊，唐晋韬，王挺，谢松县，岳大鹏，刘海池. 基于词向量语义聚类的微博热点挖掘方法 [J]. 计算机工程与科学, 2018, 40(02): 313-319.
[6]	朱书宏，兰少华. 基于OpenFlow的主动式节点失效保护机制[J]. 计算机工程与科学, 2016, 38(10): 2018-2024.
[7]	朱成阳，柴燕涛，董德尊，张鹤颖，庞征斌. 一种新的基于预约的拥塞避免机制[J]. J4, 2016, 38(02): 240-248.
[8]	徐勇. 基于价值累加理论的网络热点事件舆情研判及系统实现[J]. J4, 2015, 37(12): 2256-2261.
[9]	丁建立1,2,杨博1,2,雷雄3. 基于MapReduce的航空公司服务品质热点发现算法[J]. J4, 2013, 35(4): 130-135.
[10]	牟永敏，姜宇，张志华. 软件自动化测试中热点路径的研究[J]. J4, 2011, 33(6): 79-83.
[11]	李姗姗廖湘科朱培栋彭绍亮. 无线传感器网络中一种拥塞感知的多路径流量分配算法[J]. J4, 2008, 30(3): 86-88.
[12]	杨王黎[1] 王惠影[2]. 基于IPTV的网络影视存储系统[J]. J4, 2007, 29(11): 37-39.
[13]	陈传波李梅生. 一种基于扩展Petri网的工作流建模方法[J]. J4, 2004, 26(12): 4-7.
[14]	李晓梅张学波蒋相猛. 计算机科学与网格[J]. J4, 2004, 26(12): 49-51.
[15]	姜晓峰章建民等. WindowsDNA架构模型在证券模拟交易系统开发中的应用[J]. J4, 2001, 23(1): 71-74.

基于SDN架构的高性能网络拥塞避免策略

A high performance network congestion
avoidance protocol based on SDN architecture

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献［15］

相关文章 15

编辑推荐

Metrics

本文评价

基于SDN架构的高性能网络拥塞避免策略

A high performance network congestion avoidance protocol based on SDN architecture

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 ［15］

相关文章 15

编辑推荐

Metrics

本文评价

A high performance network congestion
avoidance protocol based on SDN architecture

参考文献［15］