Indoor Fluid Antenna Systems Enabled by Layout-Specific Modeling and Group Relative Policy Optimization
🤖 AI Summary
Indoor fluid antenna systems (FAS) suffer from challenging channel modeling and high computational complexity in joint optimization due to building structures and multipath effects.
Method: This paper proposes a layout-aware lightweight channel modeling framework and a Group-wise Relative Policy Optimization (GRPO) algorithm. It introduces a layout-specific two-ray simplified channel model enabling closed-form optimal solution derivation, and designs an advantage-estimation-based grouping mechanism for low-overhead joint optimization of antenna placement, beamforming, and power allocation.
Contribution/Results: Experiments demonstrate that the proposed channel model reduces computation time by 83.3% and improves RMSE by approximately 3 dB compared to the Sionna-based baseline. GRPO achieves superior sum-rate performance using only 49.2% of the computational resources required by standard PPO, validating its efficiency and effectiveness in optimizing indoor FAS.
Application Category
📝 Abstract
The fluid antenna system (FAS) revolutionizes wireless communications by employing position-flexible antennas that dynamically optimize channel conditions and mitigate multipath fading. This innovation is particularly valuable in indoor environments, where signal propagation is severely degraded due to structural obstructions and complex multipath reflections. In this paper, we study the channel modeling and joint optimization of antenna positioning, beamforming, and power allocation for indoor FAS. In particular, we propose, for the first time, a layout-specific channel model and a novel group relative policy optimization (GRPO) algorithm for indoor FAS. Compared to the state-of-the-art Sionna model, our approach 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 channel model enables a closed-form solution for the optimal antenna position, achieving near-optimal performance. {For the joint optimization problem, the proposed GRPO algorithm outperforms proximal policy optimization (PPO) and other baselines in sum-rate, while requiring only 49.2% computational resources of PPO, due to its group-based advantage estimation.} Simulation results reveal 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.
Problem
Research questions and friction points this paper is trying to address.
Modeling indoor fluid antenna channel layout specifics
Optimizing antenna position and beamforming jointly
Reducing computational cost while maintaining performance
Innovation
Methods, ideas, or system contributions that make the work stand out.
Layout-specific channel modeling for indoor FAS
Group relative policy optimization algorithm
Closed-form solution for optimal antenna positioning
🔎 Similar Papers
No similar papers found.
