一种面向软件定义网络的大流检测机制

doi:10.13190/j.jbupt.2019-076

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (1): 97-103.doi: 10.13190/j.jbupt.2019-076

一种面向软件定义网络的大流检测机制

邢长友¹, 李东阳¹, 谢升旭¹, 张国敏¹, 魏伟²

1. 陆军工程大学指挥控制工程学院, 南京 210001;
2. 31106部队, 南京 210016

收稿日期:2019-05-11 出版日期:2020-02-28 发布日期:2020-03-27
通讯作者: 李东阳(1996-),男,硕士生,E-mail:dongyangli_nj@126.com. E-mail:dongyangli_nj@126.com
作者简介:邢长友(1982-),男,副教授,硕士生导师,E-mail:changyouxing@126.com.
基金资助:
国家自然科学基金项目（61379149，61772271）；国家博士后科学基金项目（2017M610286）

A Heavy Hitter Detection Mechanism in Software Defined Networks

XING Chang-you¹, LI Dong-yang¹, XIE Sheng-xu¹, ZHANG Guo-min¹, WEI Wei²

1. Army Engineering University, Command and Control Engineering College, Nanjing 210001, China;
2. Corps 31106, Nanjing 210016, China

Received:2019-05-11 Online:2020-02-28 Published:2020-03-27
Supported by:

摘要/Abstract

摘要： 为解决大流检测过程中普遍存在的精度低、耗费高等问题，提出了一种面向软件定义网络的大流检测机制SampleFlow.通过综合sFlow和OpenFlow技术优势，使用粗粒度的采样技术识别出疑似大流，在OpenFlow交换机上安装测量流表项，对这些疑似大流进行细粒度测量判别，以达到准确检测大流的目标，通过采样点优化选择算法，还可降低采样的冗余性.实验结果表明，SampleFlow能够有效降低测量负载，并提升大流检测的精度.

关键词: 软件定义网络, 网络测量, 大流检测, 采样

Abstract: SampleFlow, a heavy hitter detection mechanism in software defined networks, is proposed to solve the problems of low detection accuracy and high measurement cost. By combining the technical advantage of sFlow and OpenFlow, SampleFlow firstly detects a set of suspicious heavy hitters by using the coarse-grained sFlow sampling method, and then installs measurement flow entries on specific OpenFlow switches to perform a fine-grained measurement on these suspicious heavy hitters, so as to determine the true heavy hitters. Besides, SampleFlow also uses a sampling position optimization method to decrease the sampling redundancy. Experiment results show that SampleFlow can decrease the measurement cost, and increase the heavy hitter detection accuracy effectively.

Key words: software defined network, network measurement, heavy hitter detection, sampling

中图分类号:

TP393

邢长友, 李东阳, 谢升旭, 张国敏, 魏伟. 一种面向软件定义网络的大流检测机制[J]. 北京邮电大学学报, 2020, 43(1): 97-103.

XING Chang-you, LI Dong-yang, XIE Sheng-xu, ZHANG Guo-min, WEI Wei. A Heavy Hitter Detection Mechanism in Software Defined Networks[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(1): 97-103.

参考文献

[1] The Internet Society. Cisco systems NetFlow services export version 9[EB/OL]. (2004-10)[2019-04-15]. http://www.rfc-editor.org/rfc/rfc3954.
[2] InMon. Traffic monitoring using sFlow[EB/OL]. (2013-03)[2019-04-15]. https://sflow.org/sFlow-Overview.pdf.
[3] Mai J, Chuah C N, Sridharan A, et al. Is sampled data sufficient for anomaly detection[C]//2006 ACM SIGCOMM Conference on Internet Measurement. Rio De Janeiro:ACM, 2006:165-176.
[4] Kekely L, Kucera J, Pus V, et al. Software defined monitoring of application protocols[J]. IEEE Transactions on Computers, 2016, 65(2):615-626.
[5] Yuan L, Chuah C N, Mohapatra P. ProgME:towards programmable network measurement[J]. IEEE/ACM Transactions on Networking, 2011, 19(1):115-128.
[6] Yang Tong, Jiang Jie, Liu Peng, et al. Elastic sketch:adaptive and fast network-wide measurements[C]//2018 ACM SIGCOMM Conference. Budapest:ACM, 2018:561, 575.
[7] Moshref M, Yu M, Govindan R. Resource/accuracy tradeoffs in software-defined measurement[C]//2013 ACM SIGCOMM HotSDN. Hong Kong:ACM, 2013:73-78.
[8] Harrison R, Cai Q, Gupta A, et al. Network-wide heavy hitter detection with commodity switches[C]//2018 ACM Symposium on SDN Research. Los Angeles:ACM, 2018:1-7.
[9] Moshref M, Yu M, Govindan R, et al. DREAM:dynamic resource allocation for software-defined measurement[J]. ACM SIGCOMM Computer Communication Review, 2014, 44(4):419-430.
[10] Xing Changyou, Ding Ke, Hu Chao, et al. Sample and fetch-based large flow detection mechanism in software defined networks[J]. IEEE Communications Letters, 2016, 20(9):1764-1767.
[11] Suh J, Kwon T T, Dixon C, et al. OpenSample:a low-latency, sampling-based measurement platform for commodity SDN[C]//2014 IEEE International Conference on Distributed Computing Systems. Madrid:IEEE Press, 2014:228-237.
[12] MattR. 2004 Abilene dataset[EB/OL]. (2004-05-15)[2019-04-16]. http://www.maths.adelaide.edu.au/matthew.roughan/project/traffic_matrix/.
[13] Medina A, Lakhina A, Matta I, et al. BRITE:an approach to universal topology generation[C]//2001 International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems. Cincinnati:IEEE, 2001:346-353.
[14] CAIDA. Anonymized internet traces 2014[EB/OL]. (2014-10-09)[2019-04-17]. http://www.caida.org/data/passive/passive_2014_dataset.xml.

[1]	彭维平杨玉莹宋成阎俊豪. VEC中多边缘节点协作卸载与资源分配算法[J]. 北京邮电大学学报, 2023, 46(2): 78-83.
[2]	李竟博, 马礼, 马东超, 傅颖勋, 李阳. 基于SDN的一体化融合网络路由调度机制[J]. 北京邮电大学学报, 2022, 45(4): 84-90.
[3]	李竟博马礼马东超傅颖勋李阳. 基于SDN的一体化融合网络路由调度机制[J]. 北京邮电大学学报, 2022, 45(4): 98-104.
[4]	贾雨宁, 魏翼飞, 周军华. 基于SDN与NFV的服务功能链编排算法[J]. 北京邮电大学学报, 2022, 45(2): 85-90.
[5]	刘绍华, 李明豪, 李兆歆, 毛天露, 刘京. 一种联合采样的神经网络光场[J]. 北京邮电大学学报, 2021, 44(6): 109-115.
[6]	张天骐, 叶绍鹏, 柏浩钧, 刘鉴兴. 结合编码交织的频数质心零水印算法[J]. 北京邮电大学学报, 2021, 44(5): 67-73.
[7]	邵玉斌, 刘晶, 龙华, 杜庆治, 李一民. 基于声道频谱参数的语种识别[J]. 北京邮电大学学报, 2021, 44(3): 112-119.
[8]	王敬超, 高先明, 黄玉栋, 汪硕, 黄韬. 时间敏感网络的控制架构[J]. 北京邮电大学学报, 2021, 44(2): 95-101.
[9]	马璐, 刘铭, 李超, 路兆铭, 马欢. 面向6G边缘网络的云边协同计算任务调度算法[J]. 北京邮电大学学报, 2020, 43(6): 66-73.
[10]	程超, 滕俊杰, 赵艳领, 宋梅. 一种基于多智能体强化学习的流量分配算法[J]. 北京邮电大学学报, 2019, 42(6): 43-48,57.
[11]	刘寒. 混合采样与遗传算法相结合的垃圾网页检测[J]. 北京邮电大学学报, 2019, 42(6): 111-117.
[12]	易芝玲, 崔春风, 韩双锋, 潘成康, 陈亚迷. 5G蜂窝物联网关键技术分析[J]. 北京邮电大学学报, 2018, 41(5): 20-25.
[13]	尹弼柏, 刘江, 张然, 黄韬, 刘韵洁. 基于SDN拓扑集中更新的NDN路由策略[J]. 北京邮电大学学报, 2018, 41(4): 1-8.
[14]	卢美莲, 顾云, 刘通. SDN-ScaSVNE:可伸缩的SDN生存性虚拟网络映射算法[J]. 北京邮电大学学报, 2018, 41(3): 75-80.
[15]	齐庆磊, 王文东, 龚向阳, 阙喜戎. 基于时空联合的规则放置方法[J]. 北京邮电大学学报, 2018, 41(3): 107-112.

一种面向软件定义网络的大流检测机制

A Heavy Hitter Detection Mechanism in Software Defined Networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价