D2D Communication Power Control Based on Deep Q Learning and Fractional Frequency Reuse

Underlaying Device-to-Device (D2D) communication in 5G cellular networks can improve spectrum utilization and reduce communication latency by reusing cellular networks spectrum resources. However, D2D communication can cause interference to the cellular networks. To address the problem of mutual interference between cellular user equipment (CUE) and D2D user equipment (DUE), a deep Q learning (DQL) combined with fractional frequency reuse (FFR) algorithm is proposed. Firstly, FFR is implemented to reasonably allocate frequency band resources for all users, and then the DQL algorithm is used for power control to achieve the total sum rate maximization. Simulation results show that the proposed DQL algorithm effectively improves the sum rate compared to several traditional power control algorithms, and exhibits better generalization ability and lower time overhead.