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

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.