Modelling and Predictive Congestion Control of TCP Protocols

  • Rafael C. Melo
  • Jean-Marie Farines
  • Julio E. Normey-Rico
Part of the Lecture Notes in Control and Information Sciences book series (LNCIS, volume 423)


This chapter presents the modelling and congestion control of TCP protocols. A nonlinear and a simple linear model are presented to represent TCP including comparative results with NS-2 [1] network’simulator. The simple first order plus dead-time model is selected to design two linear controllers: a generalized predictive controller (GPC) and a PI plus an Smith Predictor controller (SPPI) which are compared to a nonlinear based predictive controller (NBPC). To evaluate the TCP congestion models and controllers, different situations are simulated using NS-2 considering the presence of UDP connections. The obtained results demonstrate that the SPPI offers the best trade-off between complexity and performance to cope with the process dead time and network disturbances.


Queue Length Transmission Control Protocol Congestion Control Round Trip Time Congestion Window 
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.
    NS-2, Network Simulator (2008),
  2. 2.
    Kurose, J.F., Ross, K.W.: Computer Networking - A Top-Down Approach Featuring the Internet, 3rd edn. Addison-Wesley (2000)Google Scholar
  3. 3.
    Baiocchi, A., Vacirca, F.: TCP fluid modeling with a variable capacity bottleneck link. In: IEEE Infocom., vol. 1 (2007)Google Scholar
  4. 4.
    Jacobson, V., Karels, M.: Congestion Avoidance and Control. ACM Computer Communications Review 18(4), 314–329 (1988)CrossRefGoogle Scholar
  5. 5.
    Tang, A., Jacobsson, K., Andrew, L.L.H., Low, S.H.: Accurate Link Model and Its Application to Stability Analysis of FAST TCP. In: IEEE Infocom., vol. 1 (2007)Google Scholar
  6. 6.
    Hollot, C., Misra, V., Towsley, D., Gong, W.: A control theoretic analysis of RED. In: IEEE Infocom., vol. 1 (2001)Google Scholar
  7. 7.
    Wang, J., Wei, D.X., Low, S.H.: Modeling and stability of FAST TCP. In: Wireless Communications. IMA Volumes in Mathematics and its Applications, vol. 143, Springer Science (2006)Google Scholar
  8. 8.
    Mascolo, S.: Modeling the Internet Congestion Control Using a Smith Controller with Input Shaping. In: IFAC (2003)Google Scholar
  9. 9.
    Gerla, M.: Generalized Window Advertising for TCP Congestion Control, number 990012, 21 p (1999)Google Scholar
  10. 10.
    Hollot, C., Misra, V., Towsley, D., Gong, W.: Analysis and Design of Controllers for AQM Routers Supporting TCP Flows. IEEE/ACM Trans. Automatic Control 47(6), 945–959 (2002)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Normey-Rico, J.E., Bordons, C., Camacho, E.F.: Improving the Robustness of Dead-Time Compensating PI Controllers. Control Engineering Practice 5(6), 801–810 (1997)CrossRefGoogle Scholar
  12. 12.
    Camacho, E.F., Bordons, C.: Model Predictive Control. Springer, Berlin (2004)zbMATHCrossRefGoogle Scholar
  13. 13.
    Melo, R.C., Normey-Rico, J.E., Farines, J.M.: TCP Modelling and Predictive Congestion Control. In: IFAC (2009)Google Scholar
  14. 14.
    Melo, R.C., Normey-Rico, J.E., Farines, J.M.: Modelagem e controle de congestionamento em conexões TCP. In: Brazilian Control Conference (2008)Google Scholar
  15. 15.
    Haeri, M., Rad, A.H.M.: Adaptive model predictive TCP delay-based congestion control. Computer Communications 29 (2006)Google Scholar
  16. 16.
    Eddy, W.M., Swami, Y.P.: Adapting End Host Congestion Control for Mobility. NASA/CR-2005-213838 (2005)Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  • Rafael C. Melo
    • 1
  • Jean-Marie Farines
    • 1
  • Julio E. Normey-Rico
    • 1
  1. 1.Department of Systems and Automation (DAS)Federal University of Santa Catarina (UFSC)FlorianopolisBrazil

Personalised recommendations