Spectrum management of cognitive radio using multi-agent reinforcement learning

TLDR: This paper introduces a multi-agent reinforcement learning approach based spectrum management that uses value functions to evaluate the desirability of choosing different transmission parameters, and enables efficient assignment of spectrums and transmit powers by maximizing long-term reward.

Abstract: Wireless cognitive radio (CR) is a newly emerging paradigm that attempts to opportunistically transmit in licensed frequencies, without affecting the pre-assigned users of these bands. To enable this functionality, such a radio must predict its operational parameters, such as transmit power and spectrum. These tasks, collectively called spectrum management, is difficult to achieve in a dynamic distributed environment, in which CR users may only take local decisions, and react to the environmental changes. In this paper, we introduce a multi-agent reinforcement learning approach based spectrum management. Our approach uses value functions to evaluate the desirability of choosing different transmission parameters, and enables efficient assignment of spectrums and transmit powers by maximizing long-term reward. We then investigate various real-world scenarios, and compare the communication performance using different sets of learning parameters. We also apply Kanerva-based function approximation to improve our approach's ability to handle large cognitive radio networks and evaluate its effect on communication performance. We conclude that our reinforcement learning based spectrum management can significantly reduce the interference to the licensed users, while maintaining a high probability of successful transmissions in a cognitive radio ad hoc network.