English

Learning to Compress and Transmit: Adaptive Rate Control for Semantic Communications over LEO Satellite-to-Ground Links

Networking and Internet Architecture 2026-05-12 v1 Systems and Control Systems and Control

Abstract

The bottleneck of satellite-to-ground links poses a major challenge for the timely downlink of massive on-board imagery. This paper studies adaptive image transmission over LEO satellite-to-ground links using joint source-channel coding (JSCC). We propose an RL-based framework that dynamically selects the channel dimension (compression ratio) of a SwinJSCC encoder to maximize the number of received satisfying reconstruction-quality constraints (PSNR and MS-SSIM) within a finite visibility window. The agent leverages SNR prediction to perform proactive rate adaptation and incorporates an on-board transmission-queue model that captures bursty encoding while penalizing both buffer overflow and underutilization. Simulations under realistic overpass conditions show that the proposed policy substantially outperforms fixed-rate baselines, achieving nearly 95% qualified frames with zero packet loss.

Keywords

Cite

@article{arxiv.2605.10095,
  title  = {Learning to Compress and Transmit: Adaptive Rate Control for Semantic Communications over LEO Satellite-to-Ground Links},
  author = {Jiangtao Luo and Yongyi Ran and Guoliang Xu and Jihua Zhou},
  journal= {arXiv preprint arXiv:2605.10095},
  year   = {2026}
}