Multi-Agent Collaborative Optimization of UAV Trajectory and Latency-Aware DAG Task Offloading in UAV-Assisted MEC

The domain of UAV-assisted Multi-Access Edge Computing (MEC) emerges as a novel frontier, characterized by the seamless integration of edge computing capabilities with UAVs to facilitate advanced computational services for Terminal Devices (TDs). This research tackles two critical aspects in UAV-sup...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024-01, Vol.12, p.1-1
Main Authors: Zheng, Chunxiang, Pan, Kai, Dong, Jiadong, Chen, Lin, Guo, Qinghu, Wu, Shunfeng, Luo, Hanyun, Zhang, Xiaolin
Format: Article
Language:English
Subjects:
Algorithms
Autonomous aerial vehicles
Computation offloading
Computational modeling
Deep Reinforcement Learning
Directed Acyclic Graph
Edge computing
Energy consumption
Flight
Flight planning
Hierarchies
Mobile computing
Multi-Access Edge Computing
Multiagent systems
Optimization
Resource management
Task analysis
Task scheduling
Trajectory
Trajectory optimization
Trajectory planning
Unmanned Aerial Vehicle
Unmanned aerial vehicles
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The domain of UAV-assisted Multi-Access Edge Computing (MEC) emerges as a novel frontier, characterized by the seamless integration of edge computing capabilities with UAVs to facilitate advanced computational services for Terminal Devices (TDs). This research tackles two critical aspects in UAV-supported MEC frameworks: the strategic formulation of UAV flight paths and the refinement of execution latency for Directed Acyclic Graph (DAG) tasks. We introduce an innovative solution employing Deep Reinforcement Learning (DRL), coined as the Twin Delayed Deep Deterministic Policy Gradient for UAV Trajectory Planning and Task Offloading (TD3-TT) algorithm. This algorithm harmonizes UAV flight planning, DAG task delegation, and scheduling hierarchies, thereby enabling UAVs to efficiently undertake task offloading and processing concurrently along their designated optimal trajectories. This approach significantly diminishes the latency within the computational network. A thorough examination of simulation outcomes reveals that the TD3-TT algorithm exhibits notable convergence and robustness, surpassing conventional benchmarks and markedly reducing the execution latency of DAG tasks.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3378512