一种大象流两级识别方法

doi:10.11959/j.issn.1000-0801.2017076

电信科学 ›› 2017, Vol. 33 ›› Issue (3): 36-43.doi: 10.11959/j.issn.1000-0801.2017076

一种大象流两级识别方法

严军荣,叶景畅,潘鹏

杭州电子科技大学通信工程学院，浙江杭州310018

修回日期:2017-02-21 出版日期:2017-03-01 发布日期:2017-04-05
作者简介:严军荣（1974-），男，博士，杭州电子科技大学讲师，主要研究方向为无线通信与软件定义网络。|叶景畅（1992-），男，杭州电子科技大学硕士生，主要研究方向为软件定义网络。|潘鹏（1983-），男，博士，杭州电子科技大学副教授，主要研究方向为多用户检测技术、协作通信理论与技术。
基金资助:
浙江省公益技术应用研究计划基金资助项目(2016C31G2041123);第56批中国博士后科学基金面上资助项目(2014M561693);国家自然科学基金青年科学基金资助项目(61401130)

A two-level method for elephant flow identification

Junrong YAN,Jingchang YE,Peng PAN

School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China

Revised:2017-02-21 Online:2017-03-01 Published:2017-04-05
Supported by:
Zhejiang Provincial Public Technology Application Research Program(2016C31G2041123);The 56th China Postdoctoral Science Foundation(2014M561693);The National Natural Science Foundation of Youth Science Foundation(61401130)

摘要/Abstract

摘要：

基于大象流的识别准确度高且开销低，对于解决SDN流量管理过程中控制器单点故障问题具有重要意义。针对现有大象流识别方法识别开销大的问题，提出一种大象流两级识别方法。该方法在第一阶段提出基于TCP发送队列的可疑大象流识别算法，在第二阶段提出基于流持续时间的真实大象流识别算法；第一阶段是在端系统中识别可疑大象流，用于降低第二阶段真实大象流识别过程中SDN控制器所需监测的网络流数量。实验分析表明，在保证大象流识别的高准确度前提下，大象流两级识别方法较基于采样的大象流识别方法可以降低约85%的控制器识别开销。

关键词: 大象流识别, TCP发送队列, 软件定义网络

Abstract:

The high accuracy and low overhead of elephant flows identification have a great meaning on solving the controller's single point of failure problem in SDN traffic management.Aiming at the problem of high overhead of the existing elephant flows identification method,a two-level method for elephant flows identification was proposed which included a suspicious elephant detection algorithm based on TCP write-queue in the first stage and areal elephant detection algorithm based on flow duration in the second stage.During the first stage,the suspicious elephant flows were identified in the end systems to reduce the amount of flows monitored by the SDN controller at the second stage.Analysis and simulation prove that, under the premise of ensuring the accuracy of elephant flow identification, the two-level method for elephant flows identification reduces about 85% overhead of identification compared with sampling identification method.

Key words: elephant flow identification, TCP sending queue, SDN

中图分类号:

TP393

严军荣,叶景畅,潘鹏. 一种大象流两级识别方法[J]. 电信科学, 2017, 33(3): 36-43.

Junrong YAN,Jingchang YE,Peng PAN. A two-level method for elephant flow identification[J]. Telecommunications Science, 2017, 33(3): 36-43.

图/表 11

图1

图2

图3

表1

图4

图5

图6

表2

图7

表3

图8

参考文献 22

[1]	ZUO Q Y , CHEN M , ZHAO G S , et al. OpenFlow-based SDN technologies[J]. Journal of Software (Chinese), 2013(5): 1078-1097.
[2]	MCKEOWN N , ANDERSON T , BALAKRISHNAN H , et al. OpenFlow: enabling innovation in campus networks[J]. ACM SIGCOMM Computer Communication Review, 2008,38(2): 69-74.
[3]	CRISTIAN E , VARGHESE G . New directions in traffic measurement and accounting: focusing on the elephants, ignoring the mice[J]. ACM Transactions on Computer Systems (TOCS), 2003,21(3): 270-313.
[4]	BENSON T , AKELLA A , MALTZ D A . Network traffic characteristics of data centers in the wild[C]// The 10th ACM SIGCOMM Conference on Internet Measurement, November 1-30, 2010, Melbourne, Australia. New York: ACM Press, 2010: 267-280.
[5]	XIA J B , REN G M . Survey on elephant flow identifying methods[J]. Control and Decision, 2013,28(6): 801-807.
[6]	BI C H , LUO X , YE T , et al. On precision and scalability of elephant flow detection in data center with SDN[C]// 2013 IEEE Globecom Workshops(GC Wkshps), December 9-13, 2013, Atlanta,Georgia,USA. New Jersey: IEEE Press, 2013: 1227-1232.
[7]	MORI T , UCHIDA M , GOTO S . Identifying elephant flows through periodically sampled packets[C]// The 4th ACM SIGCOMM Conference on Internet Measurement, Oct 25-27, 2004, Taormina, Sicily, Italy. New York: ACM Press, 2004: 115-120.
[8]	ROBERT B , STROTHE R M . MJRTY-a fast majority vote algorithm[M]. Amsterdam: Springer Netherlands, 1991.
[9]	BAI L , LIU W J . Algorithm based on multiple filters for elephant flows identification[C]// 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), December 16-18, 2011, Changchun, China. New Jersey: IEEE Press, 2011: 1084-1087.
[10]	ZHAO X H , LI M H . Large flow identification based on counting bloom filter and space saving[J]. Journal of University of Chinese Academy of Sciences, 2015,32(3): 391-397.
[11]	SMITHA , KIM I , NARASIMHAREDDY A L . Identifying long-term high-bandwidth flows at a router[C]// The 8th International Conference on High Performance Computing, December 17-20, 2001, Hyderabad, India. Heidelberg: Springer, 2001: 361-371.
[12]	LIU X L , LIU Y , WANG C L . An identification algorithm of network elephant flow based on FEFS and CBF[J]. Computer Engineering, 2015,41(9): 68-73.
[13]	BAI L , TIAN L Q , CHEN C . Elephant flow detection algorithm for high speed networks based on flow sampling and LRU[J]. Computer Application and Software, 2016,33(4): 111-115.
[14]	XIE D Q , ZHOU Z H , LUO J W . An algorithm based on LRU and SCBF for elephant flows identification and its application in DDoS defense[J]. Journal of Computer Research and Development, 2011,48(8): 1517-1523.
[15]	TOOTOONCHIAN A , GHOBADI M , GANJALI Y . OpenTM:traffic matrix estimator for OpenFlow networks[C]// 2010 International Conference on Passive and Active Network Measurement, April 7-9, 2010, Zurich, Switzerland. Heidelberg: Springer, 2010: 201-210.
[16]	BENSON T , ANAND A , AKELLA A , et al. MicroTE: fine grained traffic engineering for data centers[C]// The Seventh Conference on Emerging Networking Experiments and Technologies, December 6-9, Tokyo, Japan. New York: ACM Press, 2011: 8.
[17]	LIN C Y , CHIEN C , CHANG J W , et al. Elephant flow detection in datacenters using openflow-based hierarchical statistics pulling[C]// 2014 IEEE Global Communications Conference, December 8-12, 2014, Austin, Texas, USA. New Jersey: IEEE Press, 2014: 2264-2269.
[18]	CURTIS A R , KIM W , YALAGANDULA P . Mahout:low-overhead datacenter traffic management using end-host-based elephant detection[C]// 2011 IEEE INFOCOM, April 10-15, Shanghai, China. New Jersey: IEEE Press, 2011: 1629-1637.
[19]	CHAO S C , LIN K C J , CHEN M S . Flow classification for software-defined data centers using stream mining[J]. IEEE Transactions on Services Computing. doi:10.1109/TSC 2016: 2597846.
[20]	FAN D D , MO L . Analysis of Linux kernel[M]. Beijing: China Machine Press, 2010.
[21]	OpenFlowSwitch Specification. Open networking foundation, version 1.3.0(wire protocol 0x04)[S]. IEEE Transactions on Information Theory, 2012.
[22]	KANDULA S , SENGUPTA S , GREENBERG A , et al. The nature of data center traffic: measurements ＆ analysis[C]// The 9th ACM SIGCOMM Conference on Internet Measurement Conference, November 4-6, 2009, Chicago, Illinois, USA. New York: ACM Press, 2009: 202-208.

交换机编号	流表号	五元组	状态
*	0	源/目的IP地址；源/目的端口；四层协议	suspicious/real

交换机编号	流表号	五元组	状态
5e3e089e01616580	0	10.0.0.1,1120,10.0.0.2,21,tcp	real
5e3e089e01616580	0	10.0.0.1,1123,10.0.0.2,21,tcp	real
5e3e089e01616580	0	10.0.0.1,1124,10.0.0.2,21,tcp	suspicious

参数	功能	数值
H_sum/台	主机总数	128
H_ps/台	每台交换机连接的主机数	8
S/台	交换机总数	16
Flow/条	每个终端每秒平均产生的新流数量	10
P_s	采样频率	1/50
D_s/byte	每次采样的数据量（采集分组头）	54
T/s	流表项存在时间	60

一种大象流两级识别方法

A two-level method for elephant flow identification

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 22

相关文章 15

Metrics

推荐阅读 0

[1]	唐鑫新, 曾学文, 凌致远, 宋磊. 可编程数据平面技术综述[J]. 电信科学, 2023, 39(4): 1-16.
[2]	诸葛斌, 王林超, 宋杨, 邵瑜, 董黎刚, 蒋献. 基于LSTM流量预测的路由规划和切换[J]. 电信科学, 2022, 38(8): 86-100.
[3]	刘台, 朱超, 程意, 王一鸣. 基于SDN的战术通信网络架构研究[J]. 电信科学, 2022, 38(10): 120-130.
[4]	袁硕, 任奕璟, 王则予, 孙耀华, 彭木根. 软件定义的星地融合智能无线网络[J]. 电信科学, 2021, 37(6): 66-77.
[5]	朱泓艺, 陆肖元, 李毅. 网络空间内生安全试验场管理技术[J]. 电信科学, 2021, 37(3): 66-74.
[6]	胡道允, 齐进, 陆钱春, 李锋, 房红强. 基于深度学习的流量工程算法研究与应用[J]. 电信科学, 2021, 37(2): 107-114.
[7]	王旭亮, 全硕, 刘增义, 章军. 面向6G的新型可编程网络架构研究[J]. 电信科学, 2021, 37(12): 84-92.
[8]	胡骞, 赵国永, 霍晓莉, 李俊杰, 荆瑞泉, 闫飞, 武晓锋. 灰盒光传输设备的SDN管控技术研究及应用[J]. 电信科学, 2021, 37(12): 93-100.
[9]	曹畅,张帅,刘莹,唐雄燕. 基于通信云和承载网协同的算力网络编排技术[J]. 电信科学, 2020, 36(7): 55-62.
[10]	李晶林,万晓兰. 基于端侧计算的天地一体化SDN实现思路[J]. 电信科学, 2020, 36(7): 80-91.
[11]	陈天骄,刘江,黄韬. 人工智能在网络编排系统中的应用[J]. 电信科学, 2019, 35(5): 9-16.
[12]	肖礼,袁志林,付成鹏,马卫东. 智能城域光传输网及核心光器件[J]. 电信科学, 2019, 35(4): 33-40.
[13]	冯博昊,周华春. 移动边缘计算场景下网络服务灵活适配的解决方案[J]. 电信科学, 2019, 35(3): 18-24.
[14]	王东山,马跃,李艳,高建,尹志斌. 面向电力业务的“IP数据网+光传输网”协同统一控制技术[J]. 电信科学, 2019, 35(3): 116-121.
[15]	周江,李贺武. 一种面向Portal认证的IPv6可信地址分配机制[J]. 电信科学, 2019, 35(12): 8-14.