Reinforcement Learning Based Intelligent Channel Selection Algorithm for Cognitive Radio Networks

More than an adaptive system, the cognitive radio system is an intelligent system. The reinforcement learning of the intelligent control theory is adopted in this paper, to solve the channel selection problem among the secondary users in spectrum sensing. A reinforcement learning based channel selection algorithm is proposed to increase the throughput of the secondary users. The algorithm allocates selection probabilities to the secondary users through times of interaction with the environment and self-learning, without any estimation of primary traffic. The simulation results show that compared with the traditional channel selection algorithms, the proposed algorithm can improve the throughput of the secondary users significantly, and when the primary traffic statistics are changed, it can attain convergence automatically, which could be an attempt to the future intelligent cognitive radio systems.