Distributed Multi-Agent Q-Learning for Joint Channel Allocation and Power Control in Cognitive Radio Networks

Provided by: Binary Information Press
Topic: Networking
Format: PDF
In this paper, the authors deal with the resource allocation in completely distributed cognitive radio network. They propose a form of real-time multi-agent distributed reinforcement learning, which is known as Q-learning, to allow the cognitive radio to predict its transmit power and channel, in order for achieving a high quality of service without affecting the primary users. Simulation results reveal that the proposed approach is able to significantly reduce the interference to the licensed users while maintaining a high probability of successful transmission in a cognitive radio ad-hoc network.

Find By Topic