This paper investigates a joint active and passive beamforming design for distributed simultaneous transmitting and reflecting (STAR) reconfigurable intelligent surface (RIS) assisted multi-user (MU)- mutiple input single output (MISO) systems, where the energy splitting (ES) mode is considered for the STAR-RIS. We aim to design the active beamforming vectors at the base station (BS) and the passive beamforming at the STAR-RIS to maximize the user sum rate under transmitting power constraints. The formulated problem is non-convex and nontrivial to obtain the global optimum due to the coupling between active beamforming vectors and STAR-RIS phase shifts. To efficiently solve the problem, we propose a novel graph neural network (GNN)-based framework. Specifically, we first model the interactions among users and network entities using a heterogeneous graph representation. A heterogeneous graph neural network (HGNN) implementation is then introduced to directly optimizes beamforming vectors and STAR-RIS coefficients with the system objective. Numerical results show that the proposed approach yields efficient performance compared to the previous benchmarks. Furthermore, the proposed GNN is scalable with various system configurations.

Both space and ground communications have been proven effective solutions under different perspectives in Internet of Things (IoT) networks. This article investigates multiple-access scenarios, where plenty of IoT users are cooperatively served by a satellite in space and access points (APs) on the ground. Available users in each coherence interval are split into scheduled and unscheduled subsets to optimize limited radio resources. We compute the uplink ergodic throughput of each scheduled user under imperfect channel state information (CSI) and nonorthogonal pilot signals. As maximum-radio combining is deployed locally at the ground gateway and the APs, the uplink ergodic throughput is obtained in a closed-form expression. The analytical results explicitly unveil the effects of channel conditions and pilot contamination on each scheduled user. By maximizing the sum throughput, the system can simultaneously determine scheduled users and perform power allocation based on either a model-based approach with alternating optimization or a learning-based approach with the graph neural network. Numerical results manifest that integrated satellite-terrestrial cell-free massive multiple-input-multiple-output systems can significantly improve the sum ergodic throughput over coherence intervals. The integrated systems can schedule the vast majority of users; some might be out of service due to the limited power budget.

This paper studies multiple-access scenarios where users are cooperatively served by the satellite and terrestrial access points (APs). We derive the uplink ergodic throughput of scheduled users under practical conditions where maximum-radio combining is exploited locally at the ground gateway and the APs. The analytical result explicitly unveils the effects of pilot contamination and channel conditions on the achievable throughput of each scheduled user in the uplink data transmission. The system can explicitly define the scheduled users and perform the power allocation by maximizing the sum throughput using either model-based or learning-based approaches. Numerical results demonstrate that the cooperation between space and ground systems brings superior throughput improvements over either space or ground networks. Even though most users can be simultaneously served, some may not be scheduled in each coherence interval due to limited radio resources.

This paper investigates double RIS-assisted MIMO communication systems over Rician fading channels with practical propagation conditions. Firstly, we derive the statistical channel information in closed form, which reveals the various influences of the system and the environment. Next, we study the active and passive beamforming designs for enhancing communication reliability. In particular, we propose a novel end-to-end design, where each 1-dimensional convolutional neural network (1D-CNN) represents a system entity that minimizes the symbol error rate by controlling the transceiver and RISs' phase shifts. Numerical results validate our analysis and demonstrate the superior improvements of phase shift designs to boost system performance. It is demonstrated that the proposed design can encode multiple data symbols simultaneously over different channel realizations and improve the SER performance without requiring channel information at the transmitter.

This paper investigates double RIS-assisted MIMO communication systems over Rician fading channels with finite scatterers, spatial correlation, and the existence of a double-scattering link between the transceiver. First, the statistical information is driven in closed form for the aggregated channels, unveiling various influences of the system and environment on the average channel power gains. Next, we study two active and passive beamforming designs corresponding to two objectives. The first problem maximizes channel capacity by jointly optimizing the active precoding and combining matrices at the transceivers and passive beamforming at the double RISs subject to the transmitting power constraint. In order to tackle the inherently non-convex issue, we propose an efficient alternating optimization algorithm (AO) based on the alternating direction method of multipliers (ADMM). The second problem enhances communication reliability by jointly training the encoder and decoder at the transceivers and the phase shifters at the RISs. Each neural network representing a system entity in an end-to-end learning framework is proposed to minimize the symbol error rate of the detected symbols by controlling the transceiver and the RISs’ phase shifts. Numerical results verify our analysis and demonstrate the superior improvements of phase shift designs to boost system performance.

This paper considers reconfigurable intelligent surface (RIS)-assisted point-to-point multiple-input multiple-output (MIMO) communication systems, where a transmitter communicates with a receiver through an RIS. Based on the main target of reducing the bit error rate (BER) and therefore enhancing the communication reliability, we study different model-based and data-driven (autoencoder) approaches. In particular, we consider a model-based approach that optimizes both active and passive optimization variables. We further propose a novel end-to-end data-driven framework, which leverages the recent advances in machine learning. The neural networks presented for conventional signal processing modules are jointly trained with the channel effects to minimize the bit error detection. Numerical results demonstrate that the proposed data-driven approach can learn to encode the transmitted signal via different channel realizations dynamically. In addition, the data-driven approach not only offers a significant gain in the BER performance compared to the other state-of-the-art benchmarks but also guarantees the performance when perfect channel information is unavailable.