Cooperative Downloading for LEO Satellite Networks: A DRL-Based Approach

• Published in: Sensors (Basel, Switzerland) Vol. 22; no. 18; p. 6853
• Main Authors: Choi, Hongrok, Pack, Sangheon
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2022; MDPI
• Subjects: Altitude; Analysis; Artificial satellites; Computation offloading; Data communications; Data compression; deep reinforcement learning (DRL); Downloading; Genetic algorithms; graph attention network (GAT); Ground stations; Internet access; Internet of Things; Intersatellite communications; Linear programming; low earth orbit (LEO) satellite; Low earth orbit satellites; Low earth orbits; Machine learning; Markov processes; Neural networks; Remote sensing; Satellite communications; Satellite networks; soft actor-critic (SAC); Surveillance; Testing; South Korea
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s22186853

In low earth orbit (LEO) satellite-based applications (e.g., remote sensing and surveillance), it is important to efficiently transmit collected data to ground stations (GS). However, LEO satellites’ high mobility and resultant insufficient time for downloading make this challenging. In this paper, we propose a deep-reinforcement-learning (DRL)-based cooperative downloading scheme, which utilizes inter-satellite communication links (ISLs) to fully utilize satellites’ downloading capabilities. To this end, we formulate a Markov decision problem (MDP) with the objective to maximize the amount of downloaded data. To learn the optimal approach to the formulated problem, we adopt a soft-actor-critic (SAC)-based DRL algorithm in discretized action spaces. Moreover, we design a novel neural network consisting of a graph attention network (GAT) layer to extract latent features from the satellite network and parallel fully connected (FC) layers to control individual satellites of the network. Evaluation results demonstrate that the proposed DRL-based cooperative downloading scheme can enhance the average utilization of contact time by up to 17.8% compared with independent downloading and randomly offloading schemes.