A novel multiple time scale congestion control scheme for multimedia traffic

Authors:
Hao Yin;Chuang Lin;Ting Cui;Xiao-meng Huang;Zhang-xi Tan
Affiliations:
Computer Science Department, Tsinghua University, Beijing, China;Computer Science Department, Tsinghua University, Beijing, China;Computer Science Department, Tsinghua University, Beijing, China;Computer Science Department, Tsinghua University, Beijing, China;Computer Science Department, Tsinghua University, Beijing, China
Venue:
PCM'04 Proceedings of the 5th Pacific Rim Conference on Advances in Multimedia Information Processing - Volume Part II
Year:
2004

Citing 4
Cited 0

Equation-based congestion control for unicast applications

Proceedings of the conference on Applications, Technologies, Architectures, and Protocols for Computer Communication
Network-Adaptive Rate Control and Unequal Loss Protection with TCP-Friendly Protocol for Scalable Video Over Internet

Journal of VLSI Signal Processing Systems
A multifractal wavelet model with application to network traffic

IEEE Transactions on Information Theory
A survey on TCP-friendly congestion control

IEEE Network: The Magazine of Global Internetworking

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel two time scale congestion control scheme is proposed in this paper, which is called Adaptive Wavelet and Probability-based scheme (AWP). On normal time scales of 20-200 ms, it is a smooth and TCP-friendly congestion control; on large time scales of 1-5 second, it detects persistent shifts in overall network contention and modulates the rate control exhibited on normal scale. AWP exploits self-similar property of network traffic and predicts future network available bandwidth to enhance performance, and it is adaptive to network environment changes through an auto-correction algorithm. With comparable experiments among TFRC, TCP and AWP over NS platform, AWP has been proved to be able to greatly improve the quality of service(QoS) of multimedia data transmission while avoiding congestion collapse on the network.