Performance of Resource Allocation for D2D Communications in Q-Learning Based Heterogeneous Networks

This paper investigates energy efficiency issues of device-to-device (D2D) communications in heterogeneous networks. To minimize the total transmit power, an approach based on Q-learning together with adaptive e-greedy is proposed to optimize the connection of user equipment (UE) with base station (BS) or Access point (AP). The proposed adaptive epsilon-greedy can conduct the adequate exploration and exploitation operations for effective optimization. Simulation results indicate that in the single-cell scenario, the proposed adaptive epsilon-greedy can obtain performance close to the best solution.