Multi-UAV Enabled MEC Networks: Optimizing Delay through Intelligent 3D Trajectory Planning and Resource Allocation

TL;DR

This paper presents a novel multi-UAV MEC network that optimizes delay through joint 3D trajectory planning and resource allocation, employing a new algorithm to enhance task processing efficiency in dynamic environments.

Contribution

It introduces the MUECRS algorithm for joint trajectory, computation mode, and resource optimization in multi-UAV MEC networks, addressing complex mixed action space challenges.

Findings

Achieves at least 16.7% delay reduction compared to existing methods.

Effectively designs UAV trajectories for rapid coverage and task offloading.

Demonstrates superior adaptability and robustness in dynamic scenarios.

Abstract

Mobile Edge Computing (MEC) reduces the computational burden on terminal devices by shortening the distance between these devices and computing nodes. Integrating Unmanned Aerial Vehicles (UAVs) with enhanced MEC networks can leverage the high mobility of UAVs to flexibly adjust network topology, further expanding the applicability of MEC. However, in highly dynamic and complex real-world environments, it is crucial to balance task offloading effectiveness with algorithm performance. This paper investigates a multi-UAV communication network equipped with edge computing nodes to assist terminal users in task computation. Our goal is to reduce the task processing delay for users through the joint optimization of discrete computation modes, continuous 3D trajectories, and resource assignment. To address the challenges posed by the mixed action space, we propose a Multi-UAV Edge Computing Resource Scheduling (MUECRS) algorithm, which comprises two key components: 1) trajectory optimization, and 2) computation mode and resource management. Experimental results demonstrate our method effectively designs the 3D flight trajectories of UAVs, enabling rapid terminal coverage. Furthermore, the proposed algorithm achieves efficient resource deployment and scheduling, outperforming comparative algorithms by at least 16.7%, demonstrating superior adaptability and robustness.