A fuzzy Markov game based flow controller for high-speed networks employing Metropolis criterion

A Metropolis criterion based fuzzy Markov game flow controller (MFMC) is proposed to cope with congestion problems in high-speed networks. Because of uncertainties and highly time-varying time delays, for such networks the complete and accurate information is not easy to obtain in real time The Q-learning, which is independent of mathematic model and prior knowledge and yet enables achieving good performance, is a viable alternative. The fuzzy Markov game offers a promising platform for robust control in the presence of external disturbances and unknown parameter variations that are bounded. The Metropolis criterion can cope with the balance between exploration and exploitation in action selecting. Simulation experiments demonstrate the proposed controller can learn to take the best action in order to regulate source flows. Thus it can guarantee high throughput and low packet loss ratio while efficiently avoiding the congestion.