Joint Optimization of Trajectory and Task Offloading Based on Deep Deterministic Policy Gradient in UAV-Assisted MEC

Unmanned aerial vehicles (UAVs)-assisted mobile edge computing (MEC) has emerged as a promising technology to provide computational service to ground terminal devices (TDs) with limited computing capability nowadays. This paper investigates a non-convex problem of jointly optimizing UAV trajectory a...

Full description

Saved in:
Bibliographic Details
Main Authors: Tan, Qisheng, Fu, Jielin
Format: Conference Proceeding
Language:English
Subjects:
Autonomous aerial vehicles
deep deterministic policy gradient
Delays
mobile edge computing
Multi-access edge computing
Optimization
Simulation
Task analysis
task offloading policy
Trajectory
trajectory optimization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Unmanned aerial vehicles (UAVs)-assisted mobile edge computing (MEC) has emerged as a promising technology to provide computational service to ground terminal devices (TDs) with limited computing capability nowadays. This paper investigates a non-convex problem of jointly optimizing UAV trajectory and offloading strategy in UAV assisted MEC system. To minimize the total system task execution delay, we reformulate the non-convex problem as a Markov decision process (MDP) and exploit the deep deterministic policy gradient (DDPG) algorithm to obtain the optimal flight actions and offloading strategies. Simulation results reveal that the proposed approach outperform other optimization approaches in terms of total system task delay.
ISSN:2576-7828
DOI:10.1109/ICCT59356.2023.10419420