Network Protocols and the Causes of Chaotic Traffic

Jon M. Peha
Professor and Associate Director, Center for Wireless Broadband Networks
Carnegie Mellon University
www.ece.cmu.edu/~peha

Recent empirical studies have shown that self-similar traffic models, which are rooted in chaos theory, may be more appropriate than the models typically in use for network traffic. Without an understanding of the causes of this self-similar behavior, it is difficult to say how widely applicable these models are, or what if anything should be done to mitigate the phenomenon. This research seeks potential causes of chaotic traffic. In particular, it explores whether network protocols themselves can make traffic appear chaotic over time scales of engineering interest, and if so, whether protocol modifications might help.

This work is supported in part by the National Science Foundation under Grant NCR 9706491, and by Opnet Technologies .

Some results have appeared in:

  • J. M. Peha, "Retransmission Mechanisms and Self-Similar Traffic Models," Proceedings of the IEEE/ACM/SCS Communication Networks and Distributed Systems Modeling and Simulation Conference.
  • N. Wisitpongphan and J. M. Peha, "Simulation Based Study of TCP and Self-Similarity of Network Traffic," Proceedings of Opnetwork, August 2002.
  • S. Thajchayapong and J. M. Peha, "Mobility Patterns in Micro-Cellular Wireless Networks," Proceedings of IEEE Wireless Communications and Networking Conference, March 2003.
  • N. Wisitpongphan and J. M. Peha, "Effect of TCP on Self-Similarity of Network Traffic," Proceedings of 12th IEEE International Conference on Computer Communications and Networks (ICCCN), Oct. 2003.
  • S. Thajchayapong and J. M. Peha, "Mobility Patterns in Microcellular Wireless Networks," to appear in IEEE Transactions on Mobile Computing, January 2006.