Trajectory Design and Task Scheduling for Multi-UAV Aided Mobile Edge Computing Networks

• Published in: IEEE Wireless Communications and Networking Conference : [proceedings] : WCNC pp. 1 - 6
• Main Authors: Luo, Zhanxiang, Zhang, Jiao, Wei, Jibo, Zhou, Li, Cao, Kuo, Zhao, Haitao
• Format: Conference Proceeding
• Language: English
• Published: IEEE 24.03.2025
• Subjects: Autonomous aerial vehicles; Convergence; Deep reinforcement learning; Dynamic scheduling; Heuristic algorithms; Mobile edge computing; Multi-access edge computing; multi-agent deep reinforcement learning; Optimization; Processor scheduling; Simulation; task priority; Trajectory; unmanned aerial vehicle
• ISSN: 1558-2612
• DOI: 10.1109/WCNC61545.2025.10978580

Unmanned aerial vehicles (UAVs) significantly augment mobile edge computing (MEC) networks with their flexible deployment. In this paper, we investigate a priority-driven multi-UAV cooperative MEC system, in which the task priority are jointly determined by the task queue and task type. The system aims to maximize the task priority gain, subject to the constraints on offloading decision, UAV trajectory design and task scheduling. To solve this problem, we develop a priority scheduling insert based heterogeneous Q-mixing networks (PSI-HQMIX) framework, where the PSI scheme dynamically updates the position of tasks within the queues and the HQMIX algorithm is used to obtain the optimal offloading decisions and trajectories. Simulation results demonstrate that the proposed algorithm outperforms benchmark algorithms in terms of the achieved average priority gains and convergence.