Cooperative Spectrum Sensing for Cognitive Radios using Distributed Q-Learning

In cognitive radios systems, the sparse assigned frequency bands are opened to secondary users. We consider the sensing of the frequency spectrum for cognitive radios, based on energy detection. It has been shown that the sensing reliability can be improved by using several cooperating cognitive radios that exchange their individual sensing information to a coordinator node. The coordinator node combines the received information in order to make a decision about the primary network presence. In this paper, we propose a decentralized Q-learning algorithm to share the sensing time among the cognitive radios in a way that maximize the throughputs of the radios. Numerical results show the convergence of the proposed algorithm and allow to discuss the exploration strategy, the choice of the cost function and the frequency of execution of the algorithm.