Device-to-device (D2D) communications are envisioned as a critical technology to support future ubiquitous mobile communications applications. However, the requirements of high mobility and low latency seriously constrain the performance improvement of D2D communications. In this letter, we investigate a deep reinforcement learning (DRL) based scheme of power and resource allocation for maximizing the throughput of D2D users (DUEs) and cellular users (CUEs). Based on DRL theory, D2D pairs are defined as distributed multiple agents, which aim to adaptively select the transmission power and resources to ease the co-channel interference without any prior information. Furthermore, a priority sampling based dueling double deep Q-network (PS-D3QN) distributed algorithm is proposed to help agents to learn the predominant features. Simulation results show that the proposed algorithm has higher throughput than the existing DRL algorithms with a strict delay constraint. Particularly, the probability that the agent selects high power decreases with the increase of remaining transmission time, which proves the agents effectively learn and dynamically sense the impacts of the delay constraint.
22 September 2023 in IEEE Wireless Communications Letters
Reconfigurable intelligent surface (RIS) has been envisioned as a critical technology for the future wireless communication systems. However, the inter-cell interference and the unbearable signal processing complexity seriously constrain the wide application of RIS. In this letter, we investigate a deep reinforcement learning (DRL)-based scheme of downlink beamforming and phase optimization for a multi-cell RIS-aided communication system. With the transmit power constraint, a maximization problem of average ergodic rate is formulated. We design a deep deterministic policy gradient (DDPG)-based scheme, which enables base station (BS) and RIS to intelligently control the beamforming and phase shift, respectively. Further, a DDPG-based distributed training decentralized execution algorithm is proposed to acquire the feature difference among multi-cells and maximize the average ergodic rate. Simulation results show that the proposed algorithm outperforms the other baseline algorithms, which proves the agents can effectively learn and sense the change of multi-cell interference.