A game theoretic learning solution for distributed relay selection on throughput optimization

In this paper, we study the problem of distributed relay selection in wireless networks using a game theoretic approach. Specifically, we consider a system model where one relay node can be shared by multiple source-destination pairs. Our objective is to find the relay selections of source nodes to optimize the total capacity. The relay selection problem is formulated as a congestion game with player-specific payoff functions and the existence of Nash equilibrium (NE) is demonstrated. Then we propose a stochastic learning automata (SLA) based distributed relay selection approach to obtain the NE without information exchange among source nodes. Simulation results show that the proposed distributed relay selection approach achieves satisfactory performance, when compared with other solutions.