Reinforcement Learning-Based Optimization of Quality-of-Service and Path Planning for Multi-UAV Mobile Edge Computing

Abstract

Unmanned Aerial Vehicles (UAVs) have traditionally served as network processors in mobile networks, and more recently, as mobile servers in Mobile Edge Computing (MEC). However, deploying UAVs in dynamic and obstacle-rich environments while ensuring efficient coordination among multiple UAVs presents significant challenges. To tackle these challenges, we propose a unified reinforcement learning framework for a multi-UAV MEC platform that enhances Quality-of-Service (QoS) and optimizes path planning. Specifically, our contributions include: (1) Integrating QoS optimization and UAV path planning into a unified reinforcement learning framework; (2) Modeling terminal users' demands with a sigmoid-like function to enhance service quality; (3) Incorporating terminal users' demand, risk factors, and geometric distance into the reinforcement learning reward matrix for balancing service quality, risk mitigation, and cost efficiency. Experimental results demonstrate the framework’s effectiveness: simulations in 3D environments show a 20–35% reduction in collision incidents compared to greedy algorithms and a 15–25% improvement in demand fulfillment rates under dynamic user distributions. Further analysis highlights the impact of sigmoid parameter tuning on risk-QoS trade-offs, validating the adaptability of the proposed approach in complex scenarios.