FAS-LLM: Large Language Model-Based Channel Prediction for OTFS-Enabled Satellite-FAS Links

TL;DR

This paper introduces FAS-LLM, a large language model-based approach for accurate and efficient channel prediction in OTFS-enabled satellite FAS links, significantly outperforming traditional models and preserving key physical characteristics.

Contribution

The paper presents a novel LLM-based architecture with a two-stage channel compression strategy for OTFS channels, enabling superior prediction accuracy and physical-layer fidelity.

Findings

FAS-LLM achieves up to 10 dB NMSE improvement.

Threefold RMSE reduction compared to classical models.

Predicted channels maintain key physical-layer characteristics.

Abstract

This paper proposes FAS-LLM, a novel large language model (LLM)-based architecture for predicting future channel states in Orthogonal Time Frequency Space (OTFS)-enabled satellite downlinks equipped with fluid antenna systems (FAS). The proposed method introduces a two-stage channel compression strategy combining reference-port selection and separable principal component analysis (PCA) to extract compact, delay-Doppler-aware representations from high-dimensional OTFS channels. These representations are then embedded into a LoRA-adapted LLM, enabling efficient time-series forecasting of channel coefficients. Performance evaluations demonstrate that FAS-LLM outperforms classical baselines including GRU, LSTM, and Transformer models, achieving up to 10 dB normalized mean squared error (NMSE) improvement and threefold root mean squared error (RMSE) reduction across prediction horizons. Furthermore, the predicted channels preserve key physical-layer characteristics, enabling near-optimal performance in ergodic capacity, spectral efficiency, and outage probability across a wide range of signal-to-noise ratios (SNRs). These results highlight the potential of LLM-based forecasting for delay-sensitive and energy-efficient link adaptation in future satellite IoT networks.