11 April 2024 in IEEE Communications Letters
Cell-free massive multiple-input multiple-output (MIMO) network includes numerous geographically distributed access points (APs) serving users through coherent transmission and reception. To achieve scalability, each user should be assigned a personalized cluster of APs. In this letter, we propose a deep reinforcement learning (DRL)-based approach to determine the cluster of APs for each user while satisfying constraints on minimum rates for all users, considering practical concerns such as pilot contamination and statistical channel state information (CSI). Simulation results demonstrate that the proposed DRL-based AP selection scheme outperforms other conventional schemes.
25 December 2025 in IEEE Internet of Things Journal
Multiple simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs)-aided cell-free massive multiple-input–multiple-output (CF mMIMO) network is investigated. A long-term sum-rate maximization problem is formulated to jointly optimize the active beamforming at each access point (AP) and the passive beamforming at each STAR-RIS while satisfying the quality-of-service (QoS) requirements. To address this nonconvex problem with challenges caused by user mobility and high-dimensional optimization variables, two deep reinforcement learning (DRL)-based beamforming algorithms are proposed. First, a soft actor–critic (SAC)-based centralized joint beamforming algorithm is proposed, which adds maximum entropy term to the objective function and provides an exceptional exploration–exploitation tradeoff. However, since the centralized scheme might suffer from high communication loads and latency, we generalize the proposed approach into a distributed control. A multi-agent SAC (MASAC)-based distributed beamforming algorithm is further proposed, which employs the centralized training and decentralized execution (CTDE) framework, where each AP plays the role of an agent and makes decisions based on local observations. Simulation results demonstrate that: 1) the multiple STAR-RISs can effectively improve the performance of the CF mMIMO networks compared with other baseline schemes; 2) Both SAC-based and MASAC-based beamforming algorithms can maximize the sum-rate and guarantee the QoS of users in the long term; and 3) the MASAC-based beamforming algorithm performs better and converges faster than the SAC-based beamforming algorithm, as it reduces the overall complexity and alleviates pressure on the fronthaul link transmission by making decentralized decisions.