Kiss to Abacus: A Comparison of P2P-TV Traffic Classifiers
- 560 Downloads
In the last few years the research community has proposed several techniques for network traffic classification. While the performance of these methods is promising especially for specific classes of traffic and particular network conditions, the lack of accurate comparisons among them makes it difficult to choose between them and find the most suitable technique for given needs.
Motivated also by the increase of P2P-TV traffic, this work compares Abacus, a novel behavioral classification algorithm specific for P2P-TV traffic, and Kiss, an extremely accurate statistical payload-based classifier. We first evaluate their performance on a common set of traces and later we analyze their requirements in terms of both memory occupation and CPU consumption. Our results show that the behavioral classifier can be as accurate as the payload-based with also a substantial gain in terms of computational cost, although it can deal only with a very specific type of traffic.
KeywordsOperator Trace Packet Processing Packet Payload Unknown Class Memory Occupation
Unable to display preview. Download preview PDF.
- 1.Moore, A.W., Papagiannaki, K.: Toward the Accurate Identification of Network Applications. In: Dovrolis, C. (ed.) PAM 2005. LNCS, vol. 3431, pp. 41–54. Springer, Heidelberg (2005)Google Scholar
- 2.Karagiannis, T., Broido, A., Brownlee, N., Claffy, K., Faloutsos, M.: Is p2p dying or just hiding? In: IEEE GLOBECOM 2004., Dallas, Texas, US (2004)Google Scholar
- 3.Finamore, A., Mellia, M., Meo, M., Rossi, D.: KISS: Stocastic Packet Inspection. In: Traffic Measurement and Analysis (TMA) Workshop at IFIP Networking 2009, Aachen, Germany (May 2009)Google Scholar
- 4.Cascarano, N., Risso, F., Este, A., Gringoli, F., Salgarelli, L., Finamore, A., Mellia, M.: Comparing p2ptv traffic classifiers submitted to IEEE ICC 2010 (2010)Google Scholar
- 5.Valenti, S., Rossi, D., Meo, M., Mellia, M., Bermolen, P.: Accurate, Fine-Grained Classification of P2P-TV Applications by Simply Counting Packets. In: Traffic Measurement and Analysis (TMA) Workshop at IFIP Networking 2009, Aachen, Germany (May 2009)Google Scholar
- 6.Bernaille, L., Teixeira, R., Salamatian, K.: Early application identification. In: Proc. of ACM CoNEXT 2006, Lisboa, PT (December 2006)Google Scholar
- 7.Williams, N., Zander, S., Armitage, G.: A prelimanery performance comparison of five machine learning algorithms for practical ip traffic flow comparison. ACM SIGCOMM Comp. Comm. Rev. 36(5), 7–15 (2006)Google Scholar
- 8.Erman, J., Arlitt, M., Mahanti, A.: Traffic classification using clustering algorithms. In: MineNet 2006: Mining network data (MineNet) Workshop at ACM SIGCOMM 2006, Pisa, Italy (2006)Google Scholar
- 10.Iliofotou, M., Kim, H., Pappu, P., Faloutsos, M., Mitzenmacher, M., Varghese, G.: Graph-based p2p traffic classification at the internet backbone. In: 12th IEEE Global Internet Symposium (GI 2009), Rio de Janeiro, Brazil (April 2009)Google Scholar
- 13.Kim, H., Claffy, K., Fomenkov, M., Barman, D., Faloutsos, M., Lee, K.: Internet traffic classification demystified: myths, caveats, and the best practices. In: Proc. of ACM CoNEXT 2008, Madrid, Spain (2008)Google Scholar
- 15.Hei, X., Liang, C., Liang, J., Liu, Y., Ross, K.W.: A Measurement Study of a Large-Scale P2P IPTV System. IEEE Transactions on Multimedia (December 2007)Google Scholar
- 16.Li, B., Qu, Y., Keung, Y., Xie, S., Lin, C., Liu, J., Zhang, X.: Inside the New Coolstreaming: Principles, Measurements and Performance Implications. In: IEEE INFOCOM 2008, Phoenix, AZ (April 2008)Google Scholar
- 17.Cristianini, N., Shawe-Taylor, J.: An introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, New York (1999)Google Scholar
- 18.Napa-Wine, http://www.napa-wine.eu/
- 19.Risso, F., Cascarano, N.: Diffinder, http://netgroup.polito.it/research-projects/l7-traffic-classification