A Q-learning model-independent flow controller for high-speed networks

Authors:
Xin Li;Georgi M. Dimirovski;Yuanwei Jing;Siying Zhang
Affiliations:
Faculty of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, P.R. of China;Faculty of Engineering, Computer Engg. Dept, Dogus University of Istanbul, Istanbul, Rep. of Turkey;Faculty of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, P.R. of China;Faculty of Information Science and Engineering, Northeastern University, Shenyang, Liaoning, P.R. of China
Venue:
ACC'09 Proceedings of the 2009 conference on American Control Conference
Year:
2009

Citing 7
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
A QoS-Provisioning neural fuzzy connection admission controller for multimedia high-speed networks

IEEE/ACM Transactions on Networking (TON)
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Adaptive congestion protocol: A congestion control protocol with learning capability

Computer Networks: The International Journal of Computer and Telecommunications Networking
Cooperative multiagent congestion control for high-speed networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Hierarchical neuro-fuzzy call admission controller for ATM networks

Computer Communications
Congestion control mechanisms and the best effort service model

IEEE Network: The Magazine of Global Internetworking

Quantified Score

Hi-index	0.00

Visualization

Abstract

For the congestion problems in high-speed networks, a Q-learning model-independent flow controller is proposed. Because of the uncertainties and highly time-varying, it is not easy to accurately obtain the complete information for high-speed networks. In this case, the Q-learning, which is independent of mathematic model and prior-knowledge, has good performance. In this paper, the flow with higher priority in the network is considered. The competition of the flows with different priorities is regarded as a two-player game. Through learning process, the proposed controller can achieve the optimal sending rate for the sources with lower priority while the sources with higher priority existing. Simulation results show that the proposed controller can learn to regulate source flow with the features of high throughput and low packet loss ratio, and can avoid the occurrence of congestion effectively.