Open Access

ARTICLE

DRL-Based Task Scheduling and Trajectory Control for UAV-Assisted MEC Systems

Sai Xu^1,*, Jun Liu^1,*, Shengyu Huang¹, Zhi Li²

1 School of Computer Science and Engineering, Northeastern University, Shenyang, 110169, China
2 School of Information Science and Engineering, Shenyang Ligong University, Shenyang, 110159, China

* Corresponding Authors: Sai Xu. Email: ; Jun Liu. Email:

(This article belongs to the Special Issue: Intelligent Computation and Large Machine Learning Models for Edge Intelligence in industrial Internet of Things)

Computers, Materials & Continua 2026, 86(3), 56 https://doi.org/10.32604/cmc.2025.071865

Received 13 August 2025; Accepted 28 October 2025; Issue published 12 January 2026

Abstract

In scenarios where ground-based cloud computing infrastructure is unavailable, unmanned aerial vehicles (UAVs) act as mobile edge computing (MEC) servers to provide on-demand computation services for ground terminals. To address the challenge of jointly optimizing task scheduling and UAV trajectory under limited resources and high mobility of UAVs, this paper presents PER-MATD3, a multi-agent deep reinforcement learning algorithm with prioritized experience replay (PER) into the Centralized Training with Decentralized Execution (CTDE) framework. Specifically, PER-MATD3 enables each agent to learn a decentralized policy using only local observations during execution, while leveraging a shared replay buffer with prioritized sampling and centralized critic during training to accelerate convergence and improve sample efficiency. Simulation results show that PER-MATD3 reduces average task latency by up to 23%, improves energy efficiency by 21%, and enhances service coverage compared to state-of-the-art baselines, demonstrating its effectiveness and practicality in scenarios without terrestrial networks.

---

Keywords

---