Advertisement

Improving TCP Performance over Wireless Networks Using Loss Differentiation Algorithms

  • Fabio Martignon
Conference paper
Part of the IFIP International Federation for Information Processing book series (IFIPAICT, volume 162)

Abstract

The use of loss differentiation algorithms within the congestion control scheme of TCP was proposed recently as a way of improving TCP performance over heterogeneous networks including wireless links affected by random loss. Such algorithms provide TCP with an estimate of the cause of packet losses. In this paper, we propose to use the Vegas loss differentiation algorithm to enhance the TCP NewReno error-recovery scheme, thus avoiding unnecessary rate reduction caused by packet losses induced by bit corruption on the wireless channel. We evaluate the performance of this enhanced TCP, showing that it achieves higher goodput over wireless networks, while guaranteeing fair share of network resources with classical TCP versions over wired links. Finally, by studying the TCP behavior with an ideal scheme having perfect knowledge of the cause of packet losses, we provide an upper bound to the performance of all possible schemes based on loss differentiation algorithms. The proposed TCP enhanced with Vegas loss differentiation algorithm well approaches this ideal bound.

Keywords

TCP Wireless Networks Internet Protocols 

References

  1. [A. A. Abouzeid et al., 2000]
    A.A. Abouzeid, S. Roy, and M. Azizoglu (Tel Aviv, Israel, March 2000). Stochastic Modeling of TCP over Lossy Links. In Proceedings of INFOCOM 2000.Google Scholar
  2. [Brakmo and Peterson, 1995]
    Brakmo, L. and Peterson, L. (October 1995). TCP Vegas: End-to-End Congestion Avoidance on a Global Internet. IEEE Journal on Selected Areas in Communications, 13(8): 1465–1480.CrossRefGoogle Scholar
  3. [Fu and S.C.Liew, 2003]
    Fu, C. P. and S.C. Liew (Feb. 2003). TCP Veno: TCP enhancement for transmission over wireless access networks. IEEE Journal on Selected Areas in Communications, 21(2):216–228.CrossRefGoogle Scholar
  4. [H. Balakrishnan et al., 1997]
    H. Balakrishnan, V.N. Padmanabhan, S. Seshan, and R.H. Katz (December 1997). A Comparison of Mechanisms for Improving TCP Performance over Wireless Links. IEEE/ACM Transactions on Networking, 5(6):759–769.CrossRefGoogle Scholar
  5. [High Performance Internet Research Group,]
    High Performance Internet Research Group, U. TCP Westwood Home Page, URL: http://www.cs.ucla.edu/NRL/hpi/tcpw.Google Scholar
  6. [J. Padhye et al., 1998]
    J. Padhye, V. Firoiu, D. Towsley, and J. Kurose (1998). Modeling TCP Throughput: A Simple Model and its Empirical Validation. In Proceedings of ACM SIGCOMM’ 98.Google Scholar
  7. [K. Pawlikowski et al., 2002]
    K. Pawlikowski, Jeong, H., and Lee, J. (Jan. 2002). On Credibility of Simulation Studies of Telecommunication Networks. IEEE Communications Magazine, pages 132–139.Google Scholar
  8. [M. Allman et al., 1999]
    M. Allman, V. Paxson, and W. Stevens (April 1999). TCP Congestion Control. RFC 2581.Google Scholar
  9. [N. Cardwell et al., 2000]
    N. Cardwell, S. Savage, and T. Anderson (2000). Modeling TCP Latency. In Proceedings of INFOCOM 2000, pages 1742–1751.Google Scholar
  10. ns-2 network simulator (ver.2).LBL. URL: http://www.isi.edu/nsnam.Google Scholar
  11. [S. Bregni et al., 2003]
    S. Bregni, D. Caratti, and F. Martignon (San Francisco, 1–5 Dec. 2003). Enhanced Loss Differentiation Algorithms for Use in TCP Sources over Heterogeneous Wireless Networks. In Proceedings of IEEE GLOBECOM’03.Google Scholar
  12. [S. Cen et al., 2003]
    S. Cen, P.C. Cosman, and G.M. Voelker (Oct. 2003). End-to-end Differentiation of Congestion and Wireless Losses. IEEE/ACM Transactions on Networking, 11(5):703–717.CrossRefGoogle Scholar
  13. [S. Floyd and V.Paxson, 2001]
    S. Floyd and V. Paxson (August 2001). Difficulties in Simulating the Internet. IEEE/ACM Transactions on Networking, 9:392–403.CrossRefGoogle Scholar
  14. [T. V. Lakshman and U.Madhow, 1997]
    T.V. Lakshman and U. Madhow (1997). The performance of TCP/IP for networks with high bandwidth-delay products and random loss. IEEE/ACM Transactions on Networking, 5(3):336–350.CrossRefGoogle Scholar
  15. [Wang et al., 2002]
    Wang, R., Valla, M., Sanadidi, M., and Gerla, M. (2002). Adaptive Bandwidth Share Estimation in TCP Westwood. In Proceedings of Globecom’02.Google Scholar

Copyright information

© International Federation for Information Processing 2005

Authors and Affiliations

  • Fabio Martignon
    • 1
  1. 1.Dept. of Electronics and InformationPolitecnico di MilanoMilanoItaly

Personalised recommendations