Traffic Modeling and Classification Using Packet Train Length and Packet Train Size

  • Dinil Mon Divakaran
  • Hema A. Murthy
  • Timothy A. Gonsalves
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4268)


Traffic modeling and classification finds importance in many areas such as bandwidth management, traffic analysis, traffic prediction, network planning, Quality of Service provisioning and anomalous traffic detection. Network traffic exhibits some statistically invariant properties. Earlier works show that it is possible to identify traffic based on its statistical characteristics. In this paper, an attempt is made to identify the statistically invariant properties of different traffic classes using multiple parameters, namely packet train length and packet train size. Models generated using these parameters are found to be highly accurate in classifying different traffic classes. The parameters are also useful in revealing different classes of services within different traffic classes.


Gaussian Mixture Model Vector Quantization Internet Service Provider Traffic Class Packet Header 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Croll, A., Packman, E.: Managing Bandwidth: Deploying Across Enterprise Networks. Prentice Hall PTR Internet Infrastructure Series. Prentice Hall, Englewood Cliffs (2000)Google Scholar
  2. 2.
    Floyd, S., Paxson, V.: Difficulties in simulating the Internet. IEEE/ACM Trans. on Networking 9, 392–403 (2001)CrossRefGoogle Scholar
  3. 3.
    Logg, C.: Characterization of the traffic between SLAC and the Internet (2003),
  4. 4.
    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)CrossRefGoogle Scholar
  5. 5.
    Roughan, M., Sen, S., Spatscheck, O., Duffield, N.G.: Class-of-service mapping for QoS: a statistical signature-based approach to IP traffic classification. In: Internet Measurement Conference, IMC 2004, pp. 135–148 (2004)Google Scholar
  6. 6.
    McGregor, A., Hall, M., Lorier, P., Brunskill, J.: Flow Clustering Using Machine Learning Techniques. In: Barakat, C., Pratt, I. (eds.) PAM 2004. LNCS, vol. 3015, pp. 205–214. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  7. 7.
    Chen, Y.W.: Traffic behavior analysis and modeling of sub-networks. International Journal of Network Management 12, 323–330 (2002)CrossRefGoogle Scholar
  8. 8.
    Moore, A.W., Zuev, D.: Internet traffic classification using bayesian analysis techniques. In: Proc. of the 2005 ACM SIGMETRICS, International Conference on Measurement and Modeling of Computer Systems, pp. 50–60. ACM Press, New York (2005)CrossRefGoogle Scholar
  9. 9.
    Saifulla, M.A., Murthy, H.A., Gonsalves, T.A.: Identifying Patterns in Internet Traffic. In: International Conference on Computer Communication, pp. 859–865 (2002)Google Scholar
  10. 10.
    Saifulla, M.A.: A Pattern Matching Approach To Classification Of Internet Traffic. Master’s thesis, Indian Institute of Technology, Madras (2003)Google Scholar
  11. 11.
    Tamir, D., yeon Park, C., Yoo, W.S.: Vector Quantization and Clustering: A Pyramid Approach. In: IEEE Data Compression Conference and Industrial Workshop (1995)Google Scholar
  12. 12.
    Roberts, S.J., Husmeier, D., Penny, W., Rezek, I.: Bayesian Approaches to Gaussian Mixture Modelling. IEEE Trans. on Pattern Analysis and Machine Intelligence 20, 1133–1142 (1998)CrossRefGoogle Scholar
  13. 13.
    Stevens, W.R.: TCP/IP Illustrated, The Protocols, vol. 1. Addison-Wesley, Reading (1994)Google Scholar
  14. 14.
    IANA: Internet Assigned Numbers Authority (2006),
  15. 15.
    Claffy, K.C.: Internet traffic classification. PhD thesis, University of California, San Diego (1994)Google Scholar
  16. 16.
    Paxson, V.: Empirically derived analytic models of wide-area TCP connections. IEEE/ACM Trans. on Networking 2, 316–336 (1994)CrossRefGoogle Scholar
  17. 17.
    Jain, R., Routhier, S.: Packet Trains-Measurements and a New Model for Computer Network Traffic. IEEE Journal on Selected Areas in Communications SAC-4, 986–995 (1986)CrossRefGoogle Scholar
  18. 18.
    Gray, M.R.: Vector Quantization. IEEE ASSP Magazine 1, 4–29 (1984)CrossRefGoogle Scholar
  19. 19.
    Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification, ch.2. 2nd edn. Wiley-Interscience Publication, Chichester (2001)MATHGoogle Scholar
  20. 20.
    TeNeT: The Telecommunications and Computer Networking Group, Indian Institute of Technology, Madras (1996),
  21. 21.
    Cormode, G., Korn, F., Muthukrishnan, S., Srivastava, D.: Diamond in the Rough: Finding Hierarchical Heavy Hitters in Multi-Dimensional Data. In: Proc. of the ACM SIGMOD, International Conference on Management of Data, pp. 155–166 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Dinil Mon Divakaran
    • 1
  • Hema A. Murthy
    • 1
  • Timothy A. Gonsalves
    • 1
  1. 1.Department of Computer Science and EngineeringIndian Institute of Technology, MadrasChennai

Personalised recommendations