Energy and Delay-Aware Cooperative Computing Scheme for Remote Sensing Satellite Systems

The utilization of Mobile Edge Computing (MEC) and Low Earth Orbit (LEO) remote sensing satellites offers a promising method for realizing real-time transmission of remote sensing data. However, due to the limited energy and computing resources of LEO satellites, ensuring reduced satellite energy consumption while collecting fresh data poses a significant challenge. In this paper, we explore inter-satellite cooperative computing in LEO satellite networks. LEO remote sensing satellites collect information from the Earth’s surface and offload it to computing satellites for cooperative processing. We address this problem through a two-step approach. In the first step, we decompose the original problem into three convex subproblems and derive closed-form solutions. In the second step, we formulate the offloading decision problem as a Markov decision process, using a multi-agent proximal policy optimization (MAPPO) method to minimize the combined weighted sum of energy consumption and delay. Simulation results demonstrate that our algorithm achieves better performance compared to baseline methods.