Energy-aware power control for a multiple-relay cooperative network using Q-learning

In this paper, we investigate the power control problem in a cooperative network with multiple wireless transmitters, multiple full-duplex amplify-and-forward relays, and one destination. A game-theory-based power control algorithm is devised to allocate the powers among all active nodes: the source nodes aim at maximizing their energy efficiency, whereas the relays aim at maximizing the network sum-rate. After showing that the proposed game admits multiple pure/mixed-strategy Nash equilibrium points, we formulate a Q-learning-based algorithm to let the active players converge to the best Nash equilibrium point that combines good performance in terms of both energy efficiency and overall data rate, also calling for a low computational burden. Numerical results show that the proposed scheme outperforms Nash bargaining, max-min fairness, and max-rate optimization schemes.