A Chinese restaurant game for learning and decision making in cognitive radio networks

In cognitive radio networks, secondary users (SUs) are allowed to opportunistically exploit the licensed channels. Once finding the spectrum holes, SUs need to share the available licensed channels. Therefore, one of the critical challenges for fully utilizing the spectrum resources is how the SUs obtain accurate information about the primary users’ (PUs’) activities and make right decisions on which channels to access so as to avoid competition from other SUs. In this paper, we formulate SUs’ learning and decision making process as a Chinese restaurant game, which is concerned with negative network externality, by considering the scenario where each SU senses only one of the channels and then makes access decisions sequentially. In the proposed game, SUs build the knowledge of the PUs’ activities by their own sensing and learning the information from other SUs. They also predict the subsequent SUs’ decisions to maximize their own utilities. We analyze the interactions among SUs and study specifically the impact of SUs’ initial belief, sensing accuracy and channel quality on their decisions. We also derive the theoretical results for the two-user two-channel case and extend the results to the multi-user multi-channel case. Finally, we verify the theoretical results and evaluate the performance of the proposed scheme in terms of social welfare through simulations.