Low-Altitude Satellite-AAV Collaborative Joint Mobile Edge Computing and Data Collection via Diffusion-based Deep Reinforcement Learning

TL;DR

This paper proposes a novel diffusion-based deep reinforcement learning approach for optimizing joint mobile edge computing and data collection in satellite-AAV networks, improving efficiency in remote scenarios.

Contribution

It introduces a Q-weighted variational policy optimization method that handles complex hybrid action spaces for satellite-AAV systems, a first in this context.

Findings

QAGOB outperforms five benchmark algorithms.

Joint MEC-DC optimization yields better results than separate optimization.

Diffusion models enhance policy learning efficiency.

Abstract

The integration of satellite and autonomous aerial vehicle (AAV) communications has become essential for the scenarios requiring both wide coverage and rapid deployment, particularly in remote or disaster-stricken areas where the terrestrial infrastructure is unavailable. Furthermore, emerging applications increasingly demand simultaneous mobile edge computing (MEC) and data collection (DC) capabilities within the same aerial network. However, jointly optimizing these operations in heterogeneous satellite-AAV systems presents significant challenges due to limited on-board resources and competing demands under dynamic channel conditions. In this work, we investigate a satellite-AAV-enabled joint MEC-DC system where these platforms collaborate to serve ground devices (GDs). Specifically, we formulate a joint optimization problem to minimize the average MEC end-to-end delay and AAV energy consumption while maximizing the collected data. Since the formulated optimization problem is a non-convex mixed-integer nonlinear programming (MINLP) problem, we propose a Q-weighted variational policy optimization-based joint AAV movement control, GD association, offloading decision, and bandwidth allocation (QAGOB) approach. Specifically, we reformulate the optimization problem as an action space-transformed Markov decision process to adapt the variable action dimensions and hybrid action space. Subsequently, QAGOB leverages the multi-modal generation capacities of diffusion models to optimize policies and can achieve better sample efficiency while controlling the diffusion costs during training. Simulation results show that QAGOB outperforms five other benchmarks, including traditional DRL and diffusion-based DRL algorithms. Furthermore, the MEC-DC joint optimization achieves significant advantages when compared to the separate optimization of MEC and DC.