Stochastic Game-Theoretic Spectrum Access in Distributed and Dynamic Environment

In this paper, we investigate the problem of channel selection for interference mitigation in opportunistic spectrum access networks using a stochastic game-theoretic approach. The studied network is distributed and dynamic, where each user only has its individual information, and no information exchange is available among users. Moreover, each user is considered to be dynamically active due to its specific data service requirement. Specifically, a user randomly becomes active and then competes for the wireless channel to transmit for a random duration. To capture such dynamic interactions among users, a dynamic interference graph is defined, and based on this, the interference mitigation problem is formulated as a graphical stochastic game. It is proved to be an exact potential game, in which the existence of the Nash equilibrium (NE) is guaranteed. Then, the performance bounds of the NE are theoretically analyzed. Furthermore, we design a fully distributed and online algorithm based on stochastic learning for the interference-mitigation channel selection, which is proved to converge to the NE of the formulated game. Finally, we conduct simulations to validate the effectiveness of the proposed algorithm for interference mitigation and throughput improvement in the distributed and dynamic environment.