AIGC-Assisted Digital Watermark Services in Low-Earth Orbit Satellite-Terrestrial Edge Networks

TL;DR

The paper tackles delivering personalized AIGC-based digital watermark services over a satellite-edge network by integrating LEO satellites with terrestrial endpoints. It builds a two-layer MEC architecture, defines a detailed system model including visibility, channel reliability, watermark PSNR, pricing, and end-to-end task timing, and formulates a constrained optimization problem balancing time, energy, cost, and watermark quality. A PPO-based intelligent offloading algorithm is developed to navigate the dynamic satellite visibility and heterogeneous server capabilities, using an Actor-Critic framework with clipped policy updates and GAEs. Experimental results show that PPO reduces total server cost and maintains watermark quality as the number of satellites grows, with performance further influenced by task load, iteration settings, and learning-rate decay. The work demonstrates a practical path to high-quality, low-latency AIGC services in 6G satellite–terrestrial networks, leveraging migration strategies and edge computing on moving platforms.

Abstract

Low Earth Orbit (LEO) satellite communication is a crucial component of future 6G communication networks, contributing to the development of an integrated satellite-terrestrial network. In the forthcoming satellite-to-ground network, the idle computational resources of LEO satellites can serve as edge servers, delivering intelligent task computation services to ground users. Existing research on satellite-to-ground computation primarily focuses on designing efficient task scheduling algorithms to provide straightforward computation services to ground users. This study aims to integrate satellite edge networks with Artificial Intelligence-Generated Content (AIGC) technology to offer personalized AIGC services to ground users, such as customized digital watermarking services. Firstly, we propose a satellite-to-ground edge network architecture, enabling bidirectional communication between visible LEO satellites and ground users. Each LEO satellite is equipped with intelligent algorithms supporting various AIGC-assisted digital watermarking technologies with different precision levels. Secondly, considering metrics like satellite visibility, satellite-to-ground communication stability, digital watermark quality, satellite-to-ground communication time, digital watermarking time, and ground user energy consumption, we construct an AIGC-assisted digital watermarking model based on the satellite-to-ground edge network. Finally, we introduce a reinforcement learning-based task scheduling algorithm to obtain an optimal strategy. Experimental results demonstrate that our approach effectively meets the watermark generation needs of ground users, achieving a well-balanced trade-off between generation time and user energy consumption. We anticipate that this work will provide an effective solution for the intelligent services in satellite-to-ground edge networks.

Figures (6)

• Figure 1: Satellite Coverage Model
• Figure 2: Total Computation Time
• Figure 3: Different numbers of satellites.
• Figure 4: Different numbers of tasks.
• Figure 5: Different iteration steps.