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

2026-01-12

IEEE Transactions on Mobile Computing

AI Summary

This work addresses the challenges of limited onboard resources, dynamic channels, and conflicting multi-objective requirements in satellite–autonomous aerial vehicle (AAV) cooperative networks. To balance mobile edge computing (MEC) latency, AAV energy consumption, and data collection volume, the authors propose QAGOB—a joint optimization framework for AAV trajectory planning, user association, task offloading, and bandwidth allocation. The problem is formulated as a Markov decision process with a variable action space, and for the first time, leverages the multimodal generative capability of diffusion models. By integrating variational policy optimization with a Q-weighting mechanism, QAGOB efficiently solves the resulting non-convex mixed-integer nonlinear program over a hybrid action space. Experimental results demonstrate that QAGOB significantly outperforms five baseline methods, and that the joint optimization strategy consistently surpasses independent optimization approaches in reducing latency, conserving energy, and enhancing data collection.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Multiagent Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

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.

Problem

• Satellite-AAV collaboration
• Mobile Edge Computing
• Data Collection
• Resource Optimization
• Dynamic Channel Conditions

Innovation

• Diffusion-based Deep Reinforcement Learning
• Satellite-AAV Collaboration
• Joint MEC-DC Optimization
• Action Space Transformation
• Multi-modal Policy Generation