RIS-Assisted Downlink Pinching-Antenna Systems: GNN-Enabled Optimization Approaches
This work addresses the integration of emerging pinching-antenna systems with RIS for wireless communications, offering potential improvements in sum rate and energy efficiency, but it appears incremental as it applies a novel GNN method to a specific domain problem.
The paper tackles the optimization of a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna system for multi-user downlink transmission by formulating sum rate and energy efficiency maximization problems and proposing a novel three-stage graph neural network (GNN) for unsupervised learning of PA positions, RIS phase shifts, and beamforming vectors, with numerical results validating its effectiveness, generalization capability, performance reliability, and real-time applicability.
This paper investigates a reconfigurable intelligent surface (RIS)-assisted multi-waveguide pinching-antenna (PA) system (PASS) for multi-user downlink information transmission, motivated by the unknown impact of the integration of emerging PASS and RIS on wireless communications. First, we formulate sum rate (SR) and energy efficiency (EE) maximization problems in a unified framework, subject to constraints on the movable region of PAs, total power budget, and tunable phase of RIS elements. Then, by leveraging a graph-structured topology of the RIS-assisted PASS, a novel three-stage graph neural network (GNN) is proposed, which learns PA positions based on user locations, and RIS phase shifts according to composite channel conditions at the first two stages, respectively, and finally determines beamforming vectors. Specifically, the proposed GNN is achieved through unsupervised training, together with three implementation strategies for its integration with convex optimization, thus offering trade-offs between inference time and solution optimality. Extensive numerical results are provided to validate the effectiveness of the proposed GNN, and to support its unique attributes of viable generalization capability, good performance reliability, and real-time applicability. Moreover, the impact of key parameters on RIS-assisted PASS is illustrated and analyzed.