Hybrid UAV-Enabled Secure Offloading via Deep Reinforcement Learning

Seonghoon Yoo; Seongah Jeong; Joonhyuk Kang

doi:10.1109/LWC.2023.3254554

Hybrid UAV-Enabled Secure Offloading via Deep Reinforcement Learning

Seonghoon Yoo
, Seongah Jeong
, Joonhyuk Kang

School of Advanced Fusion Studies

Korea Advanced Institute of Science and Technology

Research output: Contribution to journal › Article › peer-review

18 Scopus citations

Abstract

In this letter, we consider a secure offloading system consisting of a unmanned aerial vehicle (UAV)-mounted edge server, ground user equipments (UEs) and a malicious eavesdropper UAV. With the aim of maximizing secrecy sum-rate, we propose an adaptation of a helper UAV to switch the mode between jamming and relaying. We jointly optimize the helper UAV's trajectory and mode and UEs' offloading decision under energy budget constraints and operational limitations of nodes. The proposed algorithm is developed based on a deep deterministic policy gradient (DDPG)-based method, whose superior performances are verified via numerical results, as compared to other benchmark schemes.

Original language	English
Pages (from-to)	972-976
Number of pages	5
Journal	IEEE Wireless Communications Letters
Volume	12
Issue number	6
DOIs	https://doi.org/10.1109/LWC.2023.3254554
State	Published - 1 Jun 2023

Keywords

deep reinforcement learning
offloading
physical-layer security
Unmanned aerial vehicle (UAV)

Access to Document

10.1109/LWC.2023.3254554

Cite this

@article{b20bbcbf21e64e2a9712b8ab9155f1d2,

title = "Hybrid UAV-Enabled Secure Offloading via Deep Reinforcement Learning",

abstract = "In this letter, we consider a secure offloading system consisting of a unmanned aerial vehicle (UAV)-mounted edge server, ground user equipments (UEs) and a malicious eavesdropper UAV. With the aim of maximizing secrecy sum-rate, we propose an adaptation of a helper UAV to switch the mode between jamming and relaying. We jointly optimize the helper UAV's trajectory and mode and UEs' offloading decision under energy budget constraints and operational limitations of nodes. The proposed algorithm is developed based on a deep deterministic policy gradient (DDPG)-based method, whose superior performances are verified via numerical results, as compared to other benchmark schemes.",

keywords = "deep reinforcement learning, offloading, physical-layer security, Unmanned aerial vehicle (UAV)",

author = "Seonghoon Yoo and Seongah Jeong and Joonhyuk Kang",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2023",

month = jun,

day = "1",

doi = "10.1109/LWC.2023.3254554",

language = "English",

volume = "12",

pages = "972--976",

journal = "IEEE Wireless Communications Letters",

issn = "2162-2337",

publisher = "IEEE Communications Society",

number = "6",

}

TY - JOUR

T1 - Hybrid UAV-Enabled Secure Offloading via Deep Reinforcement Learning

AU - Yoo, Seonghoon

AU - Jeong, Seongah

AU - Kang, Joonhyuk

PY - 2023/6/1

Y1 - 2023/6/1

N2 - In this letter, we consider a secure offloading system consisting of a unmanned aerial vehicle (UAV)-mounted edge server, ground user equipments (UEs) and a malicious eavesdropper UAV. With the aim of maximizing secrecy sum-rate, we propose an adaptation of a helper UAV to switch the mode between jamming and relaying. We jointly optimize the helper UAV's trajectory and mode and UEs' offloading decision under energy budget constraints and operational limitations of nodes. The proposed algorithm is developed based on a deep deterministic policy gradient (DDPG)-based method, whose superior performances are verified via numerical results, as compared to other benchmark schemes.

AB - In this letter, we consider a secure offloading system consisting of a unmanned aerial vehicle (UAV)-mounted edge server, ground user equipments (UEs) and a malicious eavesdropper UAV. With the aim of maximizing secrecy sum-rate, we propose an adaptation of a helper UAV to switch the mode between jamming and relaying. We jointly optimize the helper UAV's trajectory and mode and UEs' offloading decision under energy budget constraints and operational limitations of nodes. The proposed algorithm is developed based on a deep deterministic policy gradient (DDPG)-based method, whose superior performances are verified via numerical results, as compared to other benchmark schemes.

KW - deep reinforcement learning

KW - offloading

KW - physical-layer security

KW - Unmanned aerial vehicle (UAV)

UR - https://www.scopus.com/pages/publications/85149817197

U2 - 10.1109/LWC.2023.3254554

DO - 10.1109/LWC.2023.3254554

M3 - Article

AN - SCOPUS:85149817197

SN - 2162-2337

VL - 12

SP - 972

EP - 976

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

IS - 6

ER -

Hybrid UAV-Enabled Secure Offloading via Deep Reinforcement Learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this