On exploiting traffic predictability in active queue management

Proceedings - IEEE INFOCOM - Tập 3 - Trang 1630-1639 vol.3
Yuan Gao1, Guanghui He2, J.C. Hou2
1Department of Electrical Engineering, Ohio State Uinversity, USA
2Department of Computer Science, University of Illinois, Urbana-Champaign, USA

Tóm tắt

In this paper, we explore the issue of exploiting traffic predictability to enhance the performance of active queue management (AQM). We show that the correlation structure present in long-range dependent traffic ran be detected on-line and used to accurately predict the future traffic. We then design, with the objective of stabilising the instantaneous queue length at a desirable level, a LMMSE-based controller, and figure in the prediction results in the calculation of the packet dropping probability. The resulting scheme is termed predictive AQM (PAQM). Through analytical reasoning, we show that PAQM is a generalized version of RED with a new dimension of congestion index - the amount of traffic that will arrive in the next few measurement intervals. By stabilizing the queue at a desirable level with consideration of future traffic, PAQM enables the link capacity to be fully utilized, while not incurring excessive packet loss. Through ns-2 simulation, we compare PAQM against existing AQM schemes with respect to different performance criteria. In particular., we show that under most cases PAQM outperforms SRED in stabilizing the instantaneous queue length, and adaptive virtual queue (AVQ) in reducing packet loss ratio and better utilizing the link capacity.

Từ khóa

#Traffic control #Communication system traffic control #Telecommunication traffic #Performance analysis #Delay #Intelligent networks #Performance loss #Queueing analysis #Algorithm design and analysis #Probability

Tài liệu tham khảo

10.1109/90.554723 10.1109/INFCOM.1999.752153 10.1016/S1389-1286(01)00304-8 lin, 0, Dynamics of random early detection, Proceedings of ACM SIGCOMM September 1997 10.1109/49.400651 10.1145/383059.383069 10.1109/90.282603 10.1109/INFCOM.2001.916670 10.1093/biomet/68.1.165 10.1109/65.923940 willinger, 1998, Self-similarity and heavy tails: Structural modeling of network traffic, A Practical Guide to Heavy Tails Statistical Techniques and Applications 10.1109/INFCOM.1999.752161 10.1109/90.731200 gao, 0, On leveraging traffic predictability in active queue management. Extended version feng, 0, Stochastic fair blue: A queue management algorithm for enforcing fairness, Proc of INFOCOM 2001 Apr 2001 10.1109/90.491008 braden, 1998, Recommendations on queue management and congestion avoidance in the internet, 10.17487/rfc2309 box, 1970, Time series analysis: Forecasting and control 10.1109/90.251892 10.1109/INFCOM.1999.752150