计算机科学 ›› 2015, Vol. 42 ›› Issue (10): 117-121.

• 网络与通信 • 上一篇    下一篇

基于混沌粒子群算法和小波SVM的P2P流量识别方法

王春枝,张会丽,叶志伟   

  1. 湖北工业大学计算机学院 武汉430068,湖北工业大学计算机学院 武汉430068,湖北工业大学计算机学院 武汉430068
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目:基于不可分小波核函数支持向量机的对等网络流量识别(61170135)资助

Peer-to-Peer Traffic identification Method Based on Chaos Particle Swarm Algorithm and Wavelet SVM

WANG Chun-zhi, ZHANG Hui-li and YE Zhi-wei   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对对等网络(Peer-to-Peer,P2P)流量具有的多尺度和突变性等问题,提出了基于小波核函数的支持向量机(Support Vector Machine,SVM)的P2P流量识别算法。进一步,对常用的SVM参数训练方法训练时间过长和易陷入局部极优值等缺陷进行分析,使用混沌粒子群算法对SVM参数进行优化以提高参数训练效率和识别准确率。最后利用真实的校园网网络流量数据对所提方法的有效性进行测试,结果表明,相对于使用传统核函数和参数训练方法的支持向量机P2P流量识别方法,所提方法具有更高的P2P流量识别正确率和计算效率。

关键词: P2P流量识别,支持向量机,小波,混沌粒子群优化算法

Abstract: A novel peer-to-peer(P2P)traffic identification algorithm was proposed as the P2P traffic has the features of multi-scale and mutability.The identification algorithm is based on support vector machine (SVM) with the wavelet kernel function.Further,the disadvantages of long training time and easily falling into local minimum in the SVM parameters training methods were analyzed,and chaos particle swarm algorithm was employed to optimize the SVM parameters in order to improve the efficiency of parameters training and the identification accuracy.Finally,the real campus network traffic data were used to test the efficiency of the proposed method.The experimental results show that the proposed method has higher identification accuracy and computational efficiency compared with the support vector machine with the traditional kernel function and parameters training method.

Key words: P2P traffic identification,Support vector machine,Wavelet,Chaos particle swarm optimization algorithm

[1] Bin Liu.A Semi-Supervised Clustering Approach for P2P Traffic Classification [J].Journal of networks,2011,6(3):424-431
[2] 鲁刚,张宏莉,叶麟.P2P流量识别[J].软件学报,2011,22(66):1281-1298 Lu Gang,Zhang Hong-li,Ye Lin.P2P traffic identification [J].Journal of Software,2011,22(66):1281-1298
[3] 张瀚.基于DPI技术的P2P流量检测系统设计[D].北京:北京邮电大学,2012 Zhang Han.Design of A P2P traffic detection system based on DPI [D].Bejing:Beijing University of Posts and Telecommunications,2012
[4] 董仕,王岗.基于UDP流量的P2P流媒体流量识别算法研究[J].通信学报,2012,33(12):25-34 Dong Shi,Wang Gang.Research on P2P streaming media identification based on UDP [J].Journal on Communications,2012,33(12):25-34
[5] Xu Ke,Zhang Ming,Ye Ming-jiang,et al.Identify P2P traffic by inspecting data transfer behavior [J].Computer Communications,2010(33):1141-1150
[6] Keralapura R,Nucci A,Chuah C-N.A novel self-learning architecture for p2p traffic classification in high speed networks [J].Computer Networks,2010(54):1055-1068
[7] 彭建芬.P2P流量识别关键技术研究[D].北京:北京邮电大学,2011 Peng Jian-fen.Research on key identification methods of P2P traffic [D].Beijing:Beijing University of Posts and Telecommunications,2012
[8] 许博,陈鸣,魏祥麟.基于隐马尔可夫模型的P2P流识别技术[J].通信学报,2012,33(6):55-63 Xu Bo,Chen Ming,Wei Xiang-lin.Hidden Markov model based P2P flow identification technique [J].Journal on Communications,2012,3(6):55-63
[9] 谭骏,陈兴蜀,杜敏,等.基于自适应BP神经网络的网络流量识别算法[J].电子科技大学学报,2012,41(4):580-585 Tan Jun,Chen Xing-shu,Du Min,et al.Internet Traffic Identification Algorithm Based on Adaptive BP Neural Network [J].Journal of University of Electronic Science and Technology of China,2012,1(4):580-585
[10] Chen H W,Hu Z B,YE Z W.Research of P2P Traffic Identification Based on Neural Network [C]∥Computer Network and Multimedia Technology,2009(CNMT 2009).Jan.2009:1-4
[11] Jin F L,Duan Y F.A P2P flow Identification Model Based on Bayesian Network [C]∥2011 7th International Conference Wireless Communications,Networking and Mobile Computing (WiCOM).Sept.2011:1-4
[12] Wang Chun-zhi,Wang Ze-qi,Ye Zhi-wei,et al.A P2P TrafficIdentification Approach Based on SVM and BFA [J].Indonesian Journal of Electrical Engineering,2013,12(4):2833-2842
[13] Liu Feng,Li Zhi-tang,Nie Qing-bin.A New Method of P2PTraffic Identification Based on Support Vector Machine at the Host Level [C]∥2009 International Conference on Information Technology and Computer Science.Kiev,Ukraine,2009:579-582
[14] 任世锦,吴铁军.基于径向基小波核的多尺度小波支持向量机[J].电路与系统学报,2008,13(4):70-76 Ren Shi-jin,Wu Tie-jun.A multi-scale wavelet support vector machine based on Radial wavelet kernel [J].Journal of Circuits and Systems,2008,13(4):70-76
[15] 刘鲭洁,陈桂明,刘小方,等.基于遗传算法的SVM参数组合优化[J].计算机应用与软件,2012,29(4):94-96,0 Liu Qing-jie,Chen Gui-ming,Liu Xiao-fang,et al.The parameter composition optimization for support vector machine based on genetic algorithm [J].Computer Application and Software,2012,9(4):94-96,0
[16] Ding Sheng,Li Shun-xin.PSO Parameters Optimization BasedSupport Vector Machines for Hyperspectral Classification [C]∥Information Science and Engineering.Wuhan,China,2009:4066-4069
[17] 高尚,杨静宇.混沌粒子群优化算法研究[J].模式识别与人工智能,2006,19(2):266-270 Gao Shang,Yang Jing-yu.Research on Chaos Particle Swarm Optimization Algorithm[J].PR & AI,2006,19(2):266-270
[18] 蒋刚.核函数理论与信号处理[M].北京:科学出版社,2013Jiang Gang.The theory of kernel functions and signals proces-sing [M].Beijing:Science Press,2013

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!