Based on a large set of TCP sessions we first study the accuracy of two well-known analytical models (SQRT and PFTK) of the TCP average rate. This study shows that these models are far from being accurate on average. Actually, our simulations show that 70% of their predictions exceed the boundaries of TCP-Friendliness, thus questioning their use in the design of new TCP-Friendly transport protocols. Our study also shows that the inaccuracy of the PFTK model is largely due to its inability to make the distinction between the two packet loss detection methods used by TCP: triple duplicate acknowledgments or timeout expirations. We then use supervised learning techniques to infer models of the TCP rate. These models show important accuracy improvements when they take into account the two types of losses. This suggests that analytical model of TCP throughput should certainly benefit from the incorporation of the timeout loss rate.


  1. 1.
    Altman, E., Avrachenkov, K., Barakat, C.: A Stochastic Model of TCP/IP with Stationary Random Losses. IEEE/ACM Transactions on Networking 13(2), 356–369 (2005)CrossRefGoogle Scholar
  2. 2.
    Baccelli, F., Hong, D.: AIMD, Fairness and fractal scaling of TCP Traffic. In: IEEE INFOCOM 2002, vol. 21, pp. 229–238 (June 2002)Google Scholar
  3. 3.
    Barakat, C.: TCP/IP modeling and validation. IEEE Network 15(3), 38–47 (2001)CrossRefGoogle Scholar
  4. 4.
    El Khayat, I., Geurts, P., Leduc, G.: Analysis and improvement of analytical models of TCP throughput by machine learning techniques. Technical report, University of Liège (2005)Google Scholar
  5. 5.
    El Khayat, I., Geurts, P., Leduc, G.: Improving TCP in wireless networks with an adaptive machine-learnt classifier of packet loss causes. In: Proc. of the International Conference on Networking, pp. 549–560. Springer, Heidelberg (2005)Google Scholar
  6. 6.
    Floyd, S., Fall, K.: Promoting the use of end-to-end congestion control in the internet. IEEE/ACM Trans. Netw. 7(4), 458–472 (1999)CrossRefGoogle Scholar
  7. 7.
    Floyd, S., Handley, M., Padhye, J., Widmer, J.: Equation-based congestion control for unicast applications. In: SIGCOMM 2000, Stockholm, Sweden, August 2000, pp. 43–56 (2000)Google Scholar
  8. 8.
    Fraleigh, C., Moon, S., Lyles, B., Cotton, C., Khan, M., Moll, D., Rockell, R., Seely, T., Diot, S.C.: Packet-level traffic measurements from the sprint ip backbone. Network, IEEE 17(6), 6–16 (2003)CrossRefGoogle Scholar
  9. 9.
    Garetto, M., Cigno, R.L., Meo, M., Marsan, M.A.: Closed queueing network models of interacting long-lived TCP flows. IEEE/ACM Trans. Netw. 12(2), 300–311 (2004)CrossRefMATHGoogle Scholar
  10. 10.
    Kumar, A.: Comparative performance analysis of versions of TCP in a local network with a lossy link. IEEE/ACM Trans. Netw. 6(4), 485–498 (1998)CrossRefGoogle Scholar
  11. 11.
    Mathis, M., Semke, J., Mahdavi, J., Ott, T.: The macroscopic behavior of the TCP congestion avoidance algorithm. ACM Computer Communication Review 27(3), 67–82 (1997)CrossRefGoogle Scholar
  12. 12.
    Misra, A., Ott, T.J.: The window distribution of idealized TCP congestion avoidance with variable packet loss. In: INFOCOM, vol. (3), pp. 1564–1572 (1999)Google Scholar
  13. 13.
    Misra, V., Gong, W.-B., Towsley, D.F.: Fluid-based analysis of a network of AQM routers supporting TCP flows with an application to RED. In: SIGCOMM, pp. 151–160 (2000)Google Scholar
  14. 14.
    Padhye, J., Firoiu, V., Towsley, D., Krusoe, J.: Modeling TCP Throughput: A Simple Model and its Empirical Validation. In: Proceedings of the ACM SIGCOMM 1998, pp. 303–314 (1998)Google Scholar
  15. 15.
    Sikdar, B., Kalyanaraman, S., Vastola, K.S.: Analytic models for the latency and steady-state throughput of tcp tahoe, reno, and sack. IEEE/ACM Trans. Netw. 11(6), 959–971 (2003)CrossRefGoogle Scholar
  16. 16.
    Sisalem, D., Wolisz, A.: MLDA: A TCP-friendly congestion control framework for heterogenous multicast environments. In: Eighth International Workshop on Quality of Service (IWQoS 2000), Pittsburgh (June 2000)Google Scholar
  17. 17.
    Widmer, J., Denda, R., Mauve, M.: A Survey on TCP-Friendly Congestion Control. IEEE Network 15(3), 28–37 (2001)CrossRefGoogle Scholar
  18. 18.
    Widmer, J., Handley, M.: Extending equation-based congestion control to multicast applications. In: Proceedings of SIGCOMM 2001, pp. 275–285. ACM Press, New York (2001)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2006

Authors and Affiliations

  • Ibtissam El Khayat
    • 1
  • Pierre Geurts
    • 1
  • Guy Leduc
    • 1
  1. 1.Department of Electrical Engineering and Computer ScienceUniversity of LiègeBelgium

Personalised recommendations