多层次P2P流量分类方法研究

计算机工程与科学

多层次P2P流量分类方法研究

陈源，林海涛

（海军工程大学电子工程学院,湖北武汉 430033）

收稿日期:2015-09-14 修回日期:2015-11-16 出版日期:2016-12-25 发布日期:2016-12-25
基金资助:
国家863计划（2009AA01Z205）；国家重点科学专项项目（2010ZX03003001）

A multilevel P2P traffic classification method

CHEN Yuan，LIN Haitao

（College of Electronics Engineering,Naval University of Engineering,Wuhan 430033,China）

Received:2015-09-14 Revised:2015-11-16 Online:2016-12-25 Published:2016-12-25

摘要/Abstract

摘要：

P2P网络流量分类对网络管理和网络安全有着十分重要的意义，由于目前P2P流量多样化的发展，传统单一的P2P流量分类方法很难对其准确分类。通过分析现阶段P2P流量分类方法的现状，结合现有P2P流量分类方法的优点，提出了多层次P2P流量分类方法，该方法由四个P2P流量分类模块组成，模块间采用分工协作及反馈机制来提升P2P流量分类的效果。实验表明该方法可以有效提升P2P流量分类准确率和效率。

关键词: P2P流量, 流量分类, 多层次, 反馈机制, 模块协作

Abstract:

P2P network traffic classification is very important for network management and network security. Because of the diverse development of P2P traffic currently, it is difficult for any single traditional P2P traffic classification method to classify P2P traffic accurately. By analyzing the current status of P2P traffic classification methods, We propose a multilevel P2P traffic classification method based on the advantages of the existing P2P traffic classification methods. It is composed of four P2P traffic modules, and the division of labor and feedback mechanism between the modules can promote the effect of P2P traffic classification. Experimental results verify its accuracy and efficiency.

Key words: P2P flow, traffic classification, multiple levels, feedback mechanism, module collaboration

陈源，林海涛. 多层次P2P流量分类方法研究[J]. 计算机工程与科学.

CHEN Yuan，LIN Haitao. A multilevel P2P traffic classification method[J]. Computer Engineering & Science.

参考文献［20］

［1］	Qin Tao, Wang Lei, Liu Zhaoli, et al.Robust application identification methods for P2P and VoIP traffic classification in backbone networks［J］.KnowledgeBased Systems,2015,82(7):152162.
［2］	Ye W,Cho K.Hybrid P2P traffic classification with heuristic rules and machine learning［J］.Soft Computing,2014,18(9):18151827.
［3］	Zhu A.A P2P network traffic classification method based on C4.5 decision tree algorithm［C］∥Proc of the 9th International Symposium on Linear Drives for Industry Applications,2014:373379.
［4］	Khalife J,Verdejo J,Hajjar A.Performance of open DPI in identifying sampled network traffic［J］.Journal of Networks,2014,8(2):7181.
［5］	Du Jiang,Long Tao.P2P traffic identification research based on the SVM［C］∥Proc of the 22nd Wireless and Optical Communication Conference,2013:683686.
［6］	Gu Bin, Zheng Guansheng, Wang Jiandong.Analysis for incremental and decrementalstandard support vector machine［J］.Journal of Software,2013,24(7):16011613.(in Chinese)
［7］	Zheng Jun,Shen Furao,Fan Hongjun.An online incremental learning support vector machine for largescale data［J］.Neural Comput and Applications,2013,22(5):10231035.
［8］	Crammer K,Singer Y.On the algorithmic implementation ofmulticlass kernelbased vector machines［J］.Journal of Machine Learning Research,2013,11(5):265292.
［9］	Hong W K,Hansson A,Deng J W.Relay autotuning of PID controllers using iterative feedback tuning［J］.Automatica,2013,39(1):149157.
［10］	Hong Y, Huang C, Yan J. Applying control theoretic approach to mitigate SIP overload［J］.Telecommunication Systems,2013,54(4):387404.
［11］	Zink T,Waldvogel M.Bittorrent traffic obfuscation:A chase towards semantic traffic identification［C］∥Proc of the 12th IEEE International Conference on PeertoPeer Computing,2012:126137.
［12］	Hu L, Zhang L. Realtime internet traffic identification based on decision trees［C］∥Proc of World Automation Congress (WAC),2012:13.
［13］	Pradhan A.Network traffic classification using support vector machines and artificial neural networks［J］.International Journal of Computer Applications 2012,8(1):812.
［14］	Park B,Hong J,Won Y.Toward finegrained traffic classification［J］.IEEE Communications Magazine, 2012,4(9):104111.
［15］	Moore A W, Papagiannaki. Toward the accurate identification of network applications［C］∥Proc of the 6th International Workshop on Passive and Active Network Measurement,2012:4145.
［16］	Karagiannis T,Broido A,Brownlee N,et al.Is P2P dying or just hiding［J］.IEEE Global Telecommunications,2012,3(2):15321538.
［17］	McGregor A, Hall M, Lorier P, et al. Flow clustering using machine learning techniques［C］∥Proc of the 5th International Workshop on Passive and Active Network Measurement,2004:205214.
［18］	Guo Wei,Wang Xichuang,Xiao Zhenjiu.P2P traffic identification based on Kfmeans and support vector machine［J］.Computer Application,2013,33(10):27342738.(in Chinese)
［19］	Wu Wei,Nie Jianyun,Gao Guanglai.Improved SVM multiple clsssifiers for image annotation［J］.Computer Engineering & Science,2015,37(7):13391343.(in Chinese)
［20］	Xue Kai, Zhou Yajian, Ping Yuan. P2P traffic forecasting model based on wavelet transform and ESN［J］.
	Computer Engineering & Design,
20	13,34(4):11471152.(in Chinese)
	附中文参考文献：
［6］	顾彬，郑关胜，王建东.增量和减量式标准支持向量机的分析［J］.软件学报，2013,24(7):16011613.
［18］	郭伟,王西闯,肖振久.基于K均值和支持向量机的P2P流量识别方法［J］.计算机应用,2013,33(10):27342738.
［19］	吴伟,聂建云,高光来.一种基于改进的支持向量机多分类器图像标注方法［J］.计算机工程与科学,2015,37(7):13391343.
［20］	薛凯,周亚建,平源.基于小波变换和ESN的P2P流量预测模型［J］.计算机工程与设计,2013,34(4):11471152.

[1]	庞兴龙, 朱国胜, 杨少龙, 李修远. 一种基于聚类与噪声的网络流量分类方法[J]. 计算机工程与科学, 2022, 44(07): 1207-1215.
[2]	高素青，王真，陈涵，袁晓萍，鲍爱华. “地理信息系统”实验教学改革研究[J]. J4, 2014, 36(A2): 154-158.
[3]	曹卫东,刘红霞. 基于多层次灰色关联分析的复杂网络节点排序模型[J]. J4, 2014, 36(06): 1165-1171.
[4]	程聂，黄昆，苏欣，张大方. 一种基于树形结构的布鲁姆过滤器[J]. J4, 2012, 34(2): 19-24.
[5]	佟玉军，周军，陈文实，杜颖，贾丹. 软件工程专业教学改革研究[J]. J4, 2011, 33(增刊A1): 49-54.
[6]	焦小焦，钟诚，杨柳，柳永念. 基于流量特征和载荷特征的P2P流量识别[J]. J4, 2010, 32(8): 24-28.
[7]	马俊, 蔡开裕, 曹华阳, 刘欣. 多层次域间路由安全监测系统的设计与实现[J]. J4, 2010, 32(2): 60-62.
[8]	陶晓玲1，胡婷2. 一种基于混合核函数的SOM网络流量分类方法[J]. J4, 2010, 32(10): 23-25.
[9]	王诚. 基于数据立方交互式多层次决策树挖掘功能实现及应用[J]. J4, 2007, 29(12): 104-106.
[10]	苏晓丽郑明春孟强. TCP友好多播拥塞控制算法研究[J]. J4, 2003, 25(4): 26-29.