Joint Offloading and Resource Allocation for Hybrid Cloud and Edge Computing in SAGINs: A Decision Assisted Hybrid Action Space Deep Reinforcement Learning Approach

TL;DR

This work tackles joint offloading and resource allocation in a space-air-ground integrated network (SAGIN) that combines LEO satellites, UAVs, and cloud servers to serve ground users with DAG-modeled tasks. It introduces a decision-assisted hybrid action space deep reinforcement learning framework (DM-SAC-H) that decouples discrete and continuous actions across multiple learners, and uses a SAC-based multi-agent setup to optimize UAV trajectories, task offloading, and cloud selection under latency and energy constraints. The method demonstrates superior performance over benchmarks in both reduced energy under latency limits and lower latency under energy constraints, highlighting the importance of ISLs and cloud integration in MEC for SAGINs. The approach offers practical appeal for real-time resource management in global coverage networks and provides a foundation for extensions to NGMA and large AI-model deployment in future networks.

Abstract

In recent years, the amalgamation of satellite communications and aerial platforms into space-air-ground integrated network (SAGINs) has emerged as an indispensable area of research for future communications due to the global coverage capacity of low Earth orbit (LEO) satellites and the flexible Deployment of aerial platforms. This paper presents a deep reinforcement learning (DRL)-based approach for the joint optimization of offloading and resource allocation in hybrid cloud and multi-access edge computing (MEC) scenarios within SAGINs. The proposed system considers the presence of multiple satellites, clouds and unmanned aerial vehicles (UAVs). The multiple tasks from ground users are modeled as directed acyclic graphs (DAGs). With the goal of reducing energy consumption and latency in MEC, we propose a novel multi-agent algorithm based on DRL that optimizes both the offloading strategy and the allocation of resources in the MEC infrastructure within SAGIN. A hybrid action algorithm is utilized to address the challenge of hybrid continuous and discrete action space in the proposed problems, and a decision-assisted DRL method is adopted to reduce the impact of unavailable actions in the training process of DRL. Through extensive simulations, the results demonstrate the efficacy of the proposed learning-based scheme, the proposed approach consistently outperforms benchmark schemes, highlighting its superior performance and potential for practical applications.

Figures (12)

• Figure 1: System model of a hybrid cloud and MEC SAGIN.
• Figure 2: The coverage provided by LEO satellites for UAVs.
• Figure 3: DAG task dependency.
• Figure 4: The framework of the hybrid action space SAC algorithm.
• Figure 5: The impact of unavailable actions on the training of deep neural networks for function approximation.