2026· IEEE Transactions on Green Communications and Networking· Vol 10, pp. 4483-4498· 0 citations· 46 references
TL;DR
A deep reinforcement learning-based proximal policy optimization (PPO) framework that jointly models the BS-RIS and RIS-user near-field spherical-wave channels under imperfect channel state information (CSI) and dynamic blockages, enabling phase-shift and adaptive beamforming optimization without predefined codebooks is proposed.
Abstract
Optimizing resource allocation (i.e., sum rate and spectral efficiency) has become essential for designing next-generation wireless networks, whose growing complexity necessitates intelligent, AI-driven solutions to enhance performance, efficiency, and adaptability. A promising solution to this problem is the use of reconfigurable intelligent surface-assisted multiple-input multiple-output (RIS-assisted MIMO) systems. When the distance between a base station (BS) and users is reduced, the antenna operates in the near-field regime, and wavefronts behave as spherical rather than planar; as a result, traditional far-field optimization techniques become ineffective. Unlike existing works that assume planar wavefronts or model only a single link, this paper proposes a deep reinforcement learning (DRL)-based proximal policy optimization (PPO) framework that jointly models the BS-RIS and RIS-user near-field spherical-wave channels under imperfect channel state information (CSI) and dynamic blockages, enabling phase-shift and adaptive beamforming optimization without predefined codebooks. Using our approach, we achieve better performance in terms of achievable rate. Extensive simulation results confirm the robustness of the proposed framework and demonstrate significant improvements over conventional methods.
Rate splitting multiple access (RSMA) has emerged as a promising non-orthogonal transmission mechanism to improve spectral- and energy efficiency, and user fairness in multi-antenna broadband channels. To further enhance its performance, in this paper we investigate a novel cooperative RSMA (C-RSMA) transmission framew...
Yuwen Cao, Hui Wang, T. Ohtsuki et al.· 0 citations
Numerical results show that the proposed impairment-aware STAR-RIS-NOMA design achieves higher sum rates and lower bit error rates than the considered hardware-impairment-unaware benchmarks.
Reconfigurable intelligent surface (RIS)-assisted cell-free massive multiple-input multiple-output (mMIMO) networks hold great potential for significantly improving wireless system capacity and energy efficiency. This paper investigates a weighted sum-rate maximization problem by jointly optimizing RIS deployment, acce...
Guang-Fei Qi, K. Sun, Wei Huang et al.· IEEE Transactions on Wireles...· 0 citations
Movable antenna (MA) and reconfigurable intelligent surface (RIS) technologies provide additional controllable degrees of freedom for improving wireless transmission. However, in RIS-enhanced MA systems, channel state information (CSI) uncertainties, transceiver hardware impairments (HWIs), and finite-resolution RIS ph...
Hao Ni, Yong-Jun Xu, Hai-Bo Zhang et al.· IEEE Transactions on Wireles...· 0 citations
Simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) can intelligently control the electromagnetic waves in the whole space through its passive components, thereby enhancing the wireless propagation environment, which is considered to be a promising technology. This paper studies th...
Ming-Yang Niu, Jun Zhang, Kai-Zhe Xu et al.· IEEE Transactions on Wireles...· 0 citations
To address severe propagation loss, frequent blockage, and distinct near-field characteristics that hinder channel state information (CSI) acquisition in STAR-RIS-assisted XL-MIMO systems, this paper investigates efficient channel estimation schemes. First, a cascaded channel model is established to accurately characte...
Da Huo, Xiao-Guang Ning, Jin-Sheng Cheng et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.