Wireless Networks

, Volume 16, Issue 2, pp 273–290 | Cite as

Enhancement of TCP over wired/wireless networks with packet loss classifiers inferred by supervised learning



TCP is suboptimal in heterogeneous wired/wireless networks because it reacts in the same way to losses due to congestion and losses due to link errors. In this paper, we propose to improve TCP performance in wired/wireless networks by endowing it with a classifier that can distinguish packet loss causes. In contrast to other proposals we do not change TCP’s congestion control nor TCP’s error recovery. A packet loss whose cause is classified as link error will simply be ignored by TCP’s congestion control and recovered as usual, while a packet loss classified as congestion loss will trigger both mechanisms as usual. To build our classification algorithm, a database of pre-classified losses is gathered by simulating a large set of random network conditions, and classification models are automatically built from this database by using supervised learning methods. Several learning algorithms are compared for this task. Our simulations of different scenarios show that adding such a classifier to TCP can improve the throughput of TCP substantially in wired/wireless networks without compromizing TCP-friendliness in both wired and wireless environments.


TCP Wireless links Loss cause classification Machine learning 


  1. 1.
    Altman, E., Barakat, C., & Ramos, V. M. (2004). Analysis of AIMD protocols over paths with variable delay. In Proceedings of IEEE INFOCOM, March 2004.Google Scholar
  2. 2.
    Bakre, A., & Badrinath, B. R. (1995). I-tcp: Indirect tcp for mobile hosts. In Proceedings of the 15th International Conference on Distributed Computing Systems.Google Scholar
  3. 3.
    Balakrishnan, H., Padmanabhan, V. N., Seshan, S., & Katz, R. H. (1996). A comparison of mechanisms for improving TCP performance over wireless links. In Conference Proceedings on Applications, Technologies, Architectures, and Protocols for Computer Communications (pp. 256–269). ACM Press.Google Scholar
  4. 4.
    Barman, D., & Matta, I. (2002). Effectiveness of loss labeling in improving tcp performance in wired/wireless networks. In Proceedings of the 10th IEEE International Conference on Network Protocols (pp. 2–11). IEEE Computer Society.Google Scholar
  5. 5.
    Barman, D., & Matta, I. (2004). Model-based loss inference by tcp over heterogeneous networks. In Proceedings of WiOpt 2004 (pp. 364–373), March 2004.Google Scholar
  6. 6.
    Biaz, S., & Vaidya, N. H. (1998). Distinguishing congestion losses from wireless transmission losses: A negative result. In Proceedings of IC3N, New Orleans.Google Scholar
  7. 7.
    Biaz, S., & Vaidya, N. H. (1999). Discriminating congestion losses from wireless losses using inter-arrival times at the receiver. In Proceedings of the 1999 IEEE Symposium on Application – Specific Systems and Software Engineering and Technology (p. 10). IEEE Computer Society.Google Scholar
  8. 8.
    Bishop, C. (1995). Neural networks for pattern recognition. Oxford: Oxford University Press.Google Scholar
  9. 9.
    Breiman, L. (1996). Bagging predictors. Machine Learning, 24(2), 123–140.MATHMathSciNetGoogle Scholar
  10. 10.
    Breiman, L., Friedman, J., Olsen, R., & Stone, C. (1984). Classification and regression trees. California: Wadsworth International.MATHGoogle Scholar
  11. 11.
    Broch, J., Maltz, D. A., Johnson, D. B., Hu, Y.-C., & Jetcheva, J. (1998). A performance comparison of multi-hop wireless ad hoc network routing protocols. In MobiCom ’98: Proceedings of the 4th Annual ACM/IEEE International Conference on Mobile Computing and Networking (pp. 85–97). New York, NY, USA: ACM Press.Google Scholar
  12. 12.
    Cen, S., Cosman, P. C., & Voelker, G. M. (2003). End-to-end differentiation of congestion and wireless losses. IEEE/ACM Transactions on Networking, 11(5), 703–717.CrossRefGoogle Scholar
  13. 13.
    Duda, R., Hart, P., Stork, D. G. (2000). Pattern classification (2nd ed.). Wiley.Google Scholar
  14. 14.
    Fawcett, T. (2004). Roc graphs: Notes and practical considerations for researchers. Technical report, HP Labs.Google Scholar
  15. 15.
    Floyd, S. (1994). TCP and explicit congestion notification. ACM Computer Communication Review, 24, 10–23.CrossRefGoogle Scholar
  16. 16.
    Floyd, S. (2001). A report on some recent developments in TCP congestion control. IEEE Communication Magazine, 39, 84–90.CrossRefGoogle Scholar
  17. 17.
    Floyd, S., Handley, M., Padhye, J., & Widmer, J. (2000). Equation-based congestion control for unicast applications. In Proceedings of SIGCOMM 2000 (pp. 43–56).Google Scholar
  18. 18.
    Freund, Y., & Schapire, R. E. (1995). A decision-theoretic generalization of on-line learning and an application to boosting. In Proceedings of the 2th European Conference on Computational Learning Theory (pp. 23–27).Google Scholar
  19. 19.
    Fu, C. P., & Liew, S. C. (2003). TCP Veno: TCP enhancement for transmission over wireless access networks. IEEE Journal on Selected Areas in Communications, 21, 216–228.CrossRefGoogle Scholar
  20. 20.
    Geurts, P., El Khayat, I., & Leduc, G. (2004). A machine learning approach to improve congestion control over wireless computer networks. In Proceedings of IEEE International Conference on Data Mining (ICDM-2004) (pp. 383–386).Google Scholar
  21. 21.
    Gurtov, A., & Floyd, S. (2004). Modeling wireless links for transport protocols. SIGCOMM Computer Communication Review, 34(2), 85–96.CrossRefGoogle Scholar
  22. 22.
    Handley, M., Padhye, J., & Floyd, S. (2003). TCP friendly rate control (TFRC): Protocol specification. RFC 3448, Proposed Standard, January 2003.Google Scholar
  23. 23.
    Hastie, T., Tibshirani, R., & Friedman, J. (2001). The elements of statistical learning: Data mining, inference and prediction. Springer.Google Scholar
  24. 24.
  25. 25.
    Lee, K.-W., & Puri, R., eun Kim T., Ramchandran, K., & Bharghavan, V. (2000). An integrated source coding and congestion control framework for video streaming in the Internet. In INFOCOM (2) (pp. 747–756).Google Scholar
  26. 26.
    Liu, J., Matta, I., & Crovella, M. (2003). End-to-end inference of loss nature in a hybrid wired/wireless environment. In Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks.Google Scholar
  27. 27.
    Mathis, M., Semke, J., Mahdavi, J. & Ott, T. (1997). The macroscopic behavior of the TCP congestion avoidance algorithm. ACM Computer Communication Review, 3, 67–82.CrossRefGoogle Scholar
  28. 28.
    McCanne S., & Floyd, S. (1997). The LBNL network simulator. Lawrence Berkeley Laboratory, http://www-nrg.ee.lbl.gov/ns. Accessed February 2005.
  29. 29.
    Medina, A., Matta, I., & Byers, J. (2000). BRITE: A flexible generator of internet topologies. Technical report, Boston University.Google Scholar
  30. 30.
    Padhye, J., Firoiu, V., Towsley, D., & Kurose, J. (2000). Modeling TCP Reno performance: A simple model and its empirical validation. IEEE/ACM Transactions on Networking, 8(2), 133–145.CrossRefGoogle Scholar
  31. 31.
    Parsa, C., & Garcia-Luna-Aceves, J. J. (1999). Improving tcp congestion control over internets with heterogeneous transmission media. In Proceedings of the Seventh Annual International Conference on Network Protocols (p. 213). IEEE Computer Society.Google Scholar
  32. 32.
    Parsa, C., & Garcia-Luna-Aceves, J. J. (2000). Differentiating congestion vs. random loss: A method for improving TCP performance over wireless links. In Proceedings of IEEE WCNC’2000 (pp. 90–93).Google Scholar
  33. 33.
    Parsa, C., & Garcia-Luna-Aceves, J. J. (2000). Improving TCP performance over wireless networks at the link layer. Mobile Networks & Applications, 5(1), 57–71.Google Scholar
  34. 34.
    Tobe, Y., Tamura, Y., Molano, A., Ghosh, S., & Tokuda, H. (2000). Achieving moderate fairness for udp flows by path-status classification. In Proceedings of the 25th Annual IEEE Conference on Local Computer Networks (p. 252). IEEE Computer Society.Google Scholar
  35. 35.
    Tsaoussidis, V., & Badr, H. (2000). TCP-Probing: Towards an error control schema with energy and throughput performance gains. In Proceedings of the 8th International Conference on Network Protocols (ICNP). IEEE Computer Society.Google Scholar
  36. 36.
    Tsaoussidis, V., & Matta, I. (2002). Open issues on TCP for mobile computing. Journal of Wireless Communication and Mobile Computing, 2, 3–20.Google Scholar
  37. 37.
    Tsaoussidis, V., & Zhang, C. (2005). The dynamics of responsiveness and smoothness in heterogeneous networks. IEEE Journal on Selected Areas in Communications, 23(6), 1178–1189.CrossRefGoogle Scholar
  38. 38.
    Wang, R., Valla, M., Sanadidi, M., Ng, B., & Gerla, M. (2002). Efficiency/friendliness tradeoffs in TCP Westwood. In Proceedings of the 7th IEEE Symposium on Computers and Communications.Google Scholar
  39. 39.
    Wu, H., Peng, Y., Long, K., Cheng, S., & Ma, J. (2002). Performance of reliable transport protocol over IEEE 802.11 wireless LAN: Analysis and enhancement. In Proceedings of INFOCOM 2002, Joint Conference of the IEEE Computer and Communications Societies (Vol. 2, pp. 599–607).Google Scholar
  40. 40.
    Xu, K., Tian, Y., & Ansari, N. (2004). TCP-Jersey for wireless IP communications. IEEE Journal on Selected Areas in Communications, 22, 747–756.CrossRefGoogle Scholar
  41. 41.
    Xylomenos, G., Polyzos, G., Mahonen, P., & Saaranen, M. (2001). TCP performance issues over wireless links. Communications Magazine, IEEE, 39(4), 52–58.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.Department of Electrical Engineering and Computer ScienceUniversity of Liège, Institut MontefioreLiègeBelgium

Personalised recommendations