Indoor Fluid Antenna Systems Enabled by Layout-Specific Modeling and Group Relative Policy Optimization
Tong Zhang, Qianren Li, Shuai Wang, Wanli Ni, Jiliang Zhang, Rui Wang, Kai-Kit Wong, Chan-Byoung Chae
TL;DR
This work addresses indoor wireless performance with fluid antenna systems by introducing a layout-specific ray-tracing channel model and a Group Relative Policy Optimization framework for joint antenna positioning, beamforming, and power allocation. The layout-aware RT model achieves an 83.3% reduction in computation time compared to Sionna RT, with about 3 dB RMSE, and a closed-form two-ray solution yields near-optimal performance in simplified settings. GRPO demonstrates superior sum-rate performance over PPO, A2C, and WMMSE baselines while using roughly half the neural-network FLOPs and about half the model size, and results indicate that increasing group size or trajectory length yields diminishing returns. The approach provides practical, scalable tools for indoor FAS optimization, combining physics-informed modeling with efficient, group-based reinforcement learning.
Abstract
Fluid antenna system (FAS) revolutionizes wireless communications via utilizing position-flexible antennas that dynamically optimize channel conditions and mitigate multipath fading. This innovation is particularly valuable in indoor environments, in which signal propagation is severely degraded due to structural obstructions and complex multipath reflections. In this paper, we investigate the channel modeling and the joint optimization of antenna positioning, beamforming, and power allocation for indoor FAS. In particular, we propose a layout-specific channel model, and employ the novel group relative policy optimization (GRPO) algorithm for tackling the optimization problem. Compared to the state-of-the-art Sionna model, our model achieves an 83.3% reduction in computation time with an approximately 3 dB increase in root-mean-square error (RMSE). When simplified to a two-ray model, our model allows for a closed-form antenna position solution with near-optimal performance. For the joint optimization problem, our GRPO algorithm outperforms proximal policy optimization (PPO) and other baselines in sum-rate, while requiring only 50.8% computational resources of PPO, thanks to its group advantage estimation. Simulation results show that increasing either the group size or trajectory length in GRPO does not yield significant improvements in sum-rate, suggesting that these parameters can be selected conservatively without sacrificing performance.