On the Validation of Traffic Classification Algorithms

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4979)


Detailed knowledge of the traffic mixture is essential for network operators and administrators, as it is a key input for numerous network management activities. Traffic classification aims at identifying the traffic mixture in the network. Several different classification approaches can be found in the literature. However, the validation of these methods is weak and ad hoc, because neither a reliable and widely accepted validation technique nor reference packet traces with well-defined content are available. In this paper, a novel validation method is proposed for characterizing the accuracy and completeness of traffic classification algorithms. The main advantages of the new method are that it is based on realistic traffic mixtures, and it enables a highly automated and reliable validation of traffic classification. As a proof-of-concept, it is examined how a state-of-the-art traffic classification method performs for the most common application types.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    IANA.TCP and UDP port numbers,
  2. 2.
  3. 3.
  4. 4.
  5. 5.
  6. 6.
  7. 7.
    The measurement created for this article,
  8. 8.
  9. 9.
  10. 10.
    Bernaille, L., Teixeira, R., Akodkenou, I., Soule, A., Salamatian, K.: Traffic classification on the fly, vol. 36, pp. 23–26. ACM Press, New York, USA (2006)Google Scholar
  11. 11.
    Erman, J., Arlitt, M., Mahanti, A.: Traffic classification using clustering algorithms. In: Proc. MineNet 2006, New York, USA (2006)Google Scholar
  12. 12.
    Karagiannis, T., Papagiannaki, K., Faloutsos, M.: BLINC: Multilevel Traffic Classification in the Dark. In: Proc. ACM SIGCOMM, Philadelphia, Pennsylvania, USA (August 2005)Google Scholar
  13. 13.
    McGregor, A., Hall, M., Lorier, P., Brunskill, A.: Flow Clustering Using Machine Learning Techniques. In: Proc. PAM, Antibes Juan-les-Pins, France (April 2004)Google Scholar
  14. 14.
    Moore, A.W., Zuev, D.: Internet Traffic Classification Using Bayesian Analysis Techniques. In: Proc. SIGMETRICS, Banff, Alberta, Canada (June 2005)Google Scholar
  15. 15.
    Perenyi, M., Molnar, S.: Enhanced skype traffic identification. In: Proc. Valuetools 2007 (2007)Google Scholar
  16. 16.
    Sen, S., Wang, J.: Analyzing peer-to-peer traffic across large networks. In: Proc. Second Annual ACM Internet Measurement Workshop (November 2002)Google Scholar
  17. 17.
    Szabó, G., Szabó, I., Orincsay, D.: Accurate traffic classification. In: Proc. IEEE WOWMoM, Helsinki, Finnland (June 2007)Google Scholar
  18. 18.
    Xu, K., Zhang, Z., Bhattacharyya, S.: Profiling Internet Backbone Traffic: Behavior Models and Applications. In: Proc. ACM SIGCOMM, Philadelphia, Pennsylvania, USA (August 2005)Google Scholar
  19. 19.
    Zander, S., Nguyen, T., Armitage, G.: Automated Traffic Classification and Application Identification Using Machine Learning. In: Proc. IEEE LCN, Sydney, Australia (November 2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  1. 1.TrafficLabEricsson ResearchBudapestHungary

Personalised recommendations