Topology-Aware Cooperative Beam-Hopping Scheduling for Efficient Resource Allocation in LEO Satellite Systems

2026-10-07

AI Summary

This study addresses the beam-hopping resource management challenges in low Earth orbit (LEO) satellite networks arising from highly dynamic topologies and heterogeneous traffic. To this end, it proposes a two-stage GNN-MAPPO cooperative framework operating under partial observability. Specifically, the method leverages graph neural networks to extract time-varying topological features and employs multi-agent proximal policy optimization for joint beam scheduling, while incorporating a load-balancing mechanism to enhance multi-satellite cooperation. Experimental results demonstrate that the proposed architecture effectively overcomes the challenges of environmental partial observability, yielding significant improvements in system energy efficiency, throughput, and user fairness.

Abstract

The dynamic topology and heterogeneous traffic demands of multi-satellite systems present substantial challenges for beam-hopping (BH) resource management. This letter develops a topology-aware cooperative BH framework for multi-satellite systems under partial observability. A lightweight load-balancing scheme first determines the serving relationships, which are then exploited to construct an association-induced satellite-user graph. A two-phase graph neural network (GNN) extracts episode-level topology-aware structural identities for parameter-sharing agents, while a recurrent multi-agent proximal policy optimization (MAPPO) policy handles slot-level dynamics for joint beam scheduling and onboard power control. Simulation results demonstrate notable gains in energy efficiency, throughput, and fairness over the baselines.

Problem

• LEO satellite systems
• beam-hopping scheduling
• resource allocation
• dynamic topology
• heterogeneous traffic demands

Innovation

• Beam-Hopping
• Graph Neural Network
• Multi-Agent Reinforcement Learning
• MAPPO
• LEO Satellite Systems