Multiagent Reinforcement Learning for Optimal Resource Allocation in Space–Air–Ground Integrated Networks

Authors:
Publisher website
Google Scholar
Abstract
This article addresses the problem of reliable task offloading in space–air–ground integrated networks (SAGIN)-assisted edge computing systems, with the goal of maximising the ratio of tasks successfully offloaded and executed within Quality-of-Service (QoS) constraints. In the considered system, ground user offload computation tasks to a satellite-mounted edge server via drones acting as relays. The formulated optimization problem jointly considers task offloading portions and bandwidth allocations across ground-to-air and air-to-space links, subject to constraints on transmission rates, total bandwidth, energy budgets, and the satellite’s computational capacity. The resulting problem is nonlinear, nonconvex, and mixed-integer, making it challenging to solve with traditional optimization techniques. To this end, we propose a deep reinforcement learning (DRL)-based solution to learn optimal offloading and resource allocation policies in dynamic environments. Furthermore, to enhance scalability and decentralized coordination, we develop a multiagent DRL framework that enables cooperative decision-making across unmanned aerial vehicles (UAVs). Simulation results demonstrate that both the single-agent and multiagent approaches achieve stable training performance, and the proposed method improves the reliable task offloading ratio by up to two times compared to benchmark schemes, while also achieving more efficient resource utilization in complex SAGIN scenarios.
Funding Information
  • Canada Excellence Research Chair (CERC) Program (CERC-2022-00109)
  • Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grant Program (RGPIN-2025-04941)
  • U.K. Engineering and Physical Sciences Research Council (EPSRC) through the EPSRC Hub on All Spectrum Connectivity (EP/X040569/1)
  • U.K. Engineering and Physical Sciences Research Council (EPSRC) through the EPSRC Hub on All Spectrum Connectivity (EP/Y037197/1)
  • National Research Foundation of Korea
  • Korean government (RS-2025 00556064)

This publication has 30 references indexed in Scilit: