| Department of Information Science and Telecommunications Dissertation Defense | ||
Title: Providing Fairness Through Detection and Preferential Dropping of High Bandwidth Unresponsive Flows When: Thursday, July 29, 2004, 10:00 AM - 12:00 PM Where: Room 503 IS Building Who: Gwyn Chatranon Committee: Dr. Sujata Banerjee, Hewlett-Packard
Laboratories, and Abstract: Stability of the Internet today depends largely on cooperation between end hosts that employ TCP that back off with network congestion. However, various types of traffic, including streaming media applications, are increasingly deployed. Such types of traffic usually do not employ end-to-end congestion control mechanism and could create an unfairness and congestion collapse problem. To avoid substantial memory requirement and complexity, fair Active Queue Management (AQM) utilizing no or partial flow state information were proposed recently to solve these problems. These schemes however exhibit several problems under different circumstances. This dissertation presents two fair AQM mechanisms, BLACK and AFC, that overcome the problems and the limitations of the existing schemes. Both BLACK and AFC need to store only a small amount of memory to maintain and exercises its fairness mechanism. Simulation studies show that both schemes outperform the other schemes in a large number of scenarios. This research also includes the comparative study of the existing techniques to estimate the number of active flows which is a crucial component for some fair AQM schemes. Further contribution presented in this dissertation is the evaluation of fair AQM schemes under the presence of various type of TCP friendly traffic which show that some fair AQM schemes that work well with UDP, may get inferior performance with TCP-friendly traffic. |
||