The robustness of the Internet today depends upon the end-to-end congestion control mechanisms of TCP. As use of non-TCP applications such as streaming media and network games grows, the potential for unfair network resource allocation and the threat of congestion collapse increase. The Internet needs a practical solution to protect well-behaving flows from misbehaving flows and avoid collapse. This paper introduces a novel statistical traffic filtering technique, Stochastic Fairness Guardian (SFG), that effectively regulates misbehaving flows with minimal traffic state information. SFG can be used in conjunction with an active queue management (AQM) mechanism to improve both network protection and efficiency. Through simulation, this paper evaluates SFG and the integration of SFG with a previously developed Aggregate Rate Controller (ARC) for TCP traffic in comparison with other similar statistical flow management mechanisms including RED-PD, SFB and CHOKe. Our results show that overall, SFG with ARC outperforms other mechanisms in terms of fairness, queuing delay, stability and TCP performance over a wide range of realistic traffic loads and conditions.
, Claypool, Mark
, Kinicki, Robert
(2005). Stochastic Fair Aggregate Rate Control: Practical Traffic Management for Efficient and Robust IP Networking. .
Retrieved from: https://digitalcommons.wpi.edu/computerscience-pubs/80