RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems

For better flexibility and greater coverage areas, Unmanned Aerial Vehicles (UAVs) have been applied in Flying Mobile Edge Computing (F-MEC) systems to offer offloading services for the User Equipment (UEs). This paper considers a disaster-affected scenario where UAVs undertake the role of MEC serve...

Full description

Saved in:
Bibliographic Details
Main Authors: Yulu Yang, Han Xu, Zhu Jin, Tiecheng Song, Jing Hu, Xiaoqin Song
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-04-01
Series:Digital Communications and Networks
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352864823001827
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729531035779072
author Yulu Yang
Han Xu
Zhu Jin
Tiecheng Song
Jing Hu
Xiaoqin Song
author_facet Yulu Yang
Han Xu
Zhu Jin
Tiecheng Song
Jing Hu
Xiaoqin Song
author_sort Yulu Yang
collection DOAJ
description For better flexibility and greater coverage areas, Unmanned Aerial Vehicles (UAVs) have been applied in Flying Mobile Edge Computing (F-MEC) systems to offer offloading services for the User Equipment (UEs). This paper considers a disaster-affected scenario where UAVs undertake the role of MEC servers to provide computing resources for Disaster Relief Devices (DRDs). Considering the fairness of DRDs, a max-min problem is formulated to optimize the saved time by jointly designing the trajectory of the UAVs, the offloading policy and serving time under the constraint of the UAVs' energy capacity. To solve the above non-convex problem, we first model the service process as a Markov Decision Process (MDP) with the Reward Shaping (RS) technique, and then propose a Deep Reinforcement Learning (DRL) based algorithm to find the optimal solution for the MDP. Simulations show that the proposed RS-DRL algorithm is valid and effective, and has better performance than the baseline algorithms.
format Article
id doaj-art-2863deff26d34c8f8c699c0a14ff8486
institution DOAJ
issn 2352-8648
language English
publishDate 2025-04-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Digital Communications and Networks
spelling doaj-art-2863deff26d34c8f8c699c0a14ff84862025-08-20T03:09:12ZengKeAi Communications Co., Ltd.Digital Communications and Networks2352-86482025-04-0111237738610.1016/j.dcan.2023.12.005RS-DRL-based offloading policy and UAV trajectory design in F-MEC systemsYulu Yang0Han Xu1Zhu Jin2Tiecheng Song3Jing Hu4Xiaoqin Song5National Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, ChinaNational Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, ChinaNational Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, ChinaNational Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, China; Corresponding author.National Mobile Communications Research Laboratory, Southeast University, Nanjing 211189, ChinaCollege of Electronic and Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics Nanjing 211106, ChinaFor better flexibility and greater coverage areas, Unmanned Aerial Vehicles (UAVs) have been applied in Flying Mobile Edge Computing (F-MEC) systems to offer offloading services for the User Equipment (UEs). This paper considers a disaster-affected scenario where UAVs undertake the role of MEC servers to provide computing resources for Disaster Relief Devices (DRDs). Considering the fairness of DRDs, a max-min problem is formulated to optimize the saved time by jointly designing the trajectory of the UAVs, the offloading policy and serving time under the constraint of the UAVs' energy capacity. To solve the above non-convex problem, we first model the service process as a Markov Decision Process (MDP) with the Reward Shaping (RS) technique, and then propose a Deep Reinforcement Learning (DRL) based algorithm to find the optimal solution for the MDP. Simulations show that the proposed RS-DRL algorithm is valid and effective, and has better performance than the baseline algorithms.http://www.sciencedirect.com/science/article/pii/S2352864823001827Flying mobile edge computingTask offloadingReward shapingDeep reinforcement learning
spellingShingle Yulu Yang
Han Xu
Zhu Jin
Tiecheng Song
Jing Hu
Xiaoqin Song
RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems
Digital Communications and Networks
Flying mobile edge computing
Task offloading
Reward shaping
Deep reinforcement learning
title RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems
title_full RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems
title_fullStr RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems
title_full_unstemmed RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems
title_short RS-DRL-based offloading policy and UAV trajectory design in F-MEC systems
title_sort rs drl based offloading policy and uav trajectory design in f mec systems
topic Flying mobile edge computing
Task offloading
Reward shaping
Deep reinforcement learning
url http://www.sciencedirect.com/science/article/pii/S2352864823001827
work_keys_str_mv AT yuluyang rsdrlbasedoffloadingpolicyanduavtrajectorydesigninfmecsystems
AT hanxu rsdrlbasedoffloadingpolicyanduavtrajectorydesigninfmecsystems
AT zhujin rsdrlbasedoffloadingpolicyanduavtrajectorydesigninfmecsystems
AT tiechengsong rsdrlbasedoffloadingpolicyanduavtrajectorydesigninfmecsystems
AT jinghu rsdrlbasedoffloadingpolicyanduavtrajectorydesigninfmecsystems
AT xiaoqinsong rsdrlbasedoffloadingpolicyanduavtrajectorydesigninfmecsystems