AirFed: Federated Graph-Enhanced Multi-Agent Reinforcement Learning for Multi-UAV Cooperative Mobile Edge Computing

2025-10-27

AI Summary

To address scalability limitations, slow convergence, and inefficient decentralized knowledge sharing in joint trajectory planning, task offloading, and resource allocation for multi-UAV-enabled mobile edge computing under dynamic and uncertain environments, this paper proposes a novel framework integrating dynamic graph attention networks (GATs), dual-actor single-critic multi-agent reinforcement learning, and reputation-driven adaptive quantized federated learning. The framework innovatively models spatio-temporal dependencies, unifies continuous control and discrete decision-making, and enables gradient-sensitive lightweight communication. Experiments demonstrate a 42.9% reduction in weighted cost, >99% deadline satisfaction rate, 94.2% IoT device coverage, 54.5% reduction in communication overhead, and strong cross-scale robustness.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Multiple Unmanned Aerial Vehicles (UAVs) cooperative Mobile Edge Computing (MEC) systems face critical challenges in coordinating trajectory planning, task offloading, and resource allocation while ensuring Quality of Service (QoS) under dynamic and uncertain environments. Existing approaches suffer from limited scalability, slow convergence, and inefficient knowledge sharing among UAVs, particularly when handling large-scale IoT device deployments with stringent deadline constraints. This paper proposes AirFed, a novel federated graph-enhanced multi-agent reinforcement learning framework that addresses these challenges through three key innovations. First, we design dual-layer dynamic Graph Attention Networks (GATs) that explicitly model spatial-temporal dependencies among UAVs and IoT devices, capturing both service relationships and collaborative interactions within the network topology. Second, we develop a dual-Actor single-Critic architecture that jointly optimizes continuous trajectory control and discrete task offloading decisions. Third, we propose a reputation-based decentralized federated learning mechanism with gradient-sensitive adaptive quantization, enabling efficient and robust knowledge sharing across heterogeneous UAVs. Extensive experiments demonstrate that AirFed achieves 42.9% reduction in weighted cost compared to state-of-the-art baselines, attains over 99% deadline satisfaction and 94.2% IoT device coverage rate, and reduces communication overhead by 54.5%. Scalability analysis confirms robust performance across varying UAV numbers, IoT device densities, and system scales, validating AirFed's practical applicability for large-scale UAV-MEC deployments.

Problem

• Optimizing UAV trajectory planning and task offloading in MEC
• Enhancing multi-agent coordination under dynamic environmental constraints
• Improving scalability and convergence in federated reinforcement learning

Innovation

• Dual-layer dynamic GATs model spatial-temporal dependencies
• Dual-Actor single-Critic optimizes trajectory and offloading decisions
• Reputation-based federated learning enables robust knowledge sharing