ABSTRACT
Identification of P2P (peer to peer) applications inside network traffic plays an important role for route provisioning, traffic policing, flow prioritization, network service pricing, network capacity planning and network resource management. Inspecting and identifying the P2P applications is one of the most important tasks to have a network that runs efficiently. In this paper, we focus on identification of different P2P applications. To this end, we explore four commonly used supervised machine learning algorithms as C4.5, Ripper, SVM(Support Vector Machines), Naïve Bayesian and well known unsupervised machine learning algorithm K-Means on four different datasets. We evaluate their performances to identify the P2P applications that each traffic flow belongs to. Evaluations show that, Ripper algorithm gives better results than the others.
- Alpaydin, E. 2004. Introduction to Machine Learning, MIT Press. Google ScholarDigital Library
- Burges, C. J. C. 1998. A Tutorial on Support Vector Machines for Pattern Recognition, Data Mining and Knowledge Discovery, Volume 2, pp. 1--47. Google ScholarDigital Library
- George, H. and Langley, P. 1995. Estimating Continuous Distributions in Bayesian Classifiers, Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence. pp. 338--345, Morgan Kaufmann, San Mateo. Google ScholarDigital Library
- Hyunchul, K., Claffy, K. C., Fomenkov, M., Barman, D., Faloutsos , M., and Lee, K. 2008. Internet traffic classification demystified: myths, caveats, and the best practices, Proceedings of the 2008 ACM CoNEXT Conference, p.1--12, Madrid, Spain. Google ScholarDigital Library
- Liu, F., Li, Z., and Nie, Q., 2009. A New Method of P2P Traffic Identification Based on Support Vector Machine at the Host Level, International Conference on Information Technology and Computer Science, ITCS 2009, Volume 2, pp. 579--582, Kiev, Ukraine. Google ScholarDigital Library
- Alshammari, R., and Zincir-Heywood, A.N., 2009. Machine learning based encrypted traffic classification: Identifying SSH and Skype, IEEE Symposium on Computational Intelligence for Security and Defense Applications, CISDA 2009, pp.1--8, Ottawa, Canada. Google ScholarDigital Library
- Wang, J., Zhang, J., and Tan, Y, 2011. Research of P2P traffic identification based on traffic characteristics, International Conference on Multimedia Technology, ICMT 2011, pp.5032--5035, Hangzhou, China.Google Scholar
- Liu, T., and Chen, X., 2011. A novel approach to detect P2P traffic based on program behavior analysis, International Conference on Electrical and Control Engineering, ICECE 2011, pp.5677--5680, Yichang, China.Google Scholar
- Soysal, M., and Schmidt, E.G., 2007. An accurate evaluation of machine learning algorithms for flow-based P2P traffic detection, 22nd International Symposium on Computer and Information Sciences, ISCIS 2007, pp.1--6, Ankara, Turkey.Google Scholar
- Kun, L., Wei, G., 2010. Feedback model based on P2P traffic control, International Conference on Computational Problem Solving, ICCP 201, pp.35--38, Lijiang, China.Google Scholar
- Guanghui, H., Hou, J., Chen, W. P., Hamada, T., 2007, One Size Does Not Fit All: A Detailed Analysis and Modeling of P2P Traffic, Global Telecommunications Conference, IEEE GLOBECOM 2007, pp.393--398, Washington, US.Google Scholar
- Chunzhi, W., Wei., J., Hong, C., Luo, W., Fang, H., 2010. Research on a method of P2P traffic identification based on multi-dimension characteristics, 5th International Conference on Computer Science and Education, ICCSE 2010, pp.1010--1013, Hefei, China.Google ScholarCross Ref
- BitCommet P2P file sharing software, http://www.bitcomet.com/Google Scholar
- BitTorrent P2P file sharing software, http://www.bittorrent.com/Google Scholar
- UTorrent P2P file sharing software, http://www.utorrent.com/Google Scholar
- Netmate network measurement tool, http://www.ip-measurement.org/tools/netmateGoogle Scholar
- Alshammari, R., Zincir-Heywood, A. N., 2010. An investigation on the identification of VoIP traffic: Case study on Gtalk and Skype, International Conference on Network and Service Management, CNSM 2010,pp.310--313, Niagara Falls, Canada.Google ScholarCross Ref
- Calculating Flow Statistics using NetMate: http://dan.arndt.ca/nims/calculating-flow-statistics-using-netmate/Google Scholar
- Quinlan, J.R., 1993. C4.5: Programs for Machine Learning, Morgan Kaufmann Publishers, ISBN:1--55860--238-0. Google ScholarDigital Library
- Weka software http://www.cs.waikato.ac.nz/ml/wekaGoogle Scholar
Index Terms
- A Preliminary Investigation on the Identification of Peer to Peer Network Applications
Recommendations
Efficient resource discovery in self-organized unstructured peer-to-peer networks
In unstructured peer-to-peer (P2P) networks, two autonomous peer nodes can be connected if users in those nodes are interested in each other's data. Owing to the similarity between P2P networks and social networks, where peer nodes can be regarded as ...
Federation Based Solution for Peer-to-Peer Network Management
ICCS '07: Proceedings of the 7th international conference on Computational Science, Part IV: ICCS 2007Recently, Peer-to-Peer (P2P) technology has become one of the hottest topics in the research area of Internet. With a variety of P2P applications, especially those applications sharing large-size file resources among a large scale of user community, ...
Comments