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

TL;DR

This paper introduces an RL-based adaptive rate control framework for satellite image transmission over LEO links, optimizing quality and throughput amid variable channel conditions.

Contribution

It presents a novel joint source-channel coding approach with reinforcement learning for dynamic rate adaptation in satellite communications.

Findings

Achieves nearly 95% qualified frames with zero packet loss.

Outperforms fixed-rate baselines in realistic simulations.

Effectively manages bursty encoding and buffer constraints.

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.