Learning to Compress and Transmit: Adaptive Rate Control for Semantic Communications over LEO Satellite-to-Ground Links
2026-05-11 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors address the problem of quickly sending large amounts of images from low Earth orbit satellites to the ground, which is difficult due to limited communication time. They use a method that combines how images are compressed and sent over the channel, adapting the compression based on predicted signal quality. Their approach involves a smart agent that changes the amount of compression to fit within the available transmission time without overloading the system. Simulations show their method sends more high-quality images successfully compared to fixed compression settings.
LEO satellitejoint source-channel codingSwinJSCCreinforcement learningcompression ratiosignal-to-noise ratio (SNR)rate adaptationPSNRMS-SSIMbuffer management
Authors
Jiangtao Luo, Yongyi Ran, Guoliang Xu, Jihua Zhou
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.