Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems

This paper examines a cognitive radio (CR) nonorthogonal multiple access (NOMA) system in which an unmanned aerial vehicle equipped with a reconfigurable intelligent surface (UAV-RIS) plays two roles: relaying and friendly jamming. The communication protocol has two phases. The first is an energy ha...

Full description

Saved in:
Bibliographic Details
Main Authors: Van Nhan Vo, Nguyen Quoc Long, Viet-Hung Dang, Tu Dac Ho, Hung Tran, Symeon Chatzinotas, Dinh-Hieu Tran, Surasak Sanguanpong, Chakchai So-In
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of the Communications Society
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10980338/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849340463237038080
author Van Nhan Vo
Nguyen Quoc Long
Viet-Hung Dang
Tu Dac Ho
Hung Tran
Symeon Chatzinotas
Dinh-Hieu Tran
Surasak Sanguanpong
Chakchai So-In
author_facet Van Nhan Vo
Nguyen Quoc Long
Viet-Hung Dang
Tu Dac Ho
Hung Tran
Symeon Chatzinotas
Dinh-Hieu Tran
Surasak Sanguanpong
Chakchai So-In
author_sort Van Nhan Vo
collection DOAJ
description This paper examines a cognitive radio (CR) nonorthogonal multiple access (NOMA) system in which an unmanned aerial vehicle equipped with a reconfigurable intelligent surface (UAV-RIS) plays two roles: relaying and friendly jamming. The communication protocol has two phases. The first is an energy harvesting phase in which the UAV harvests radio frequency energy from a power beacon. In the second phase, a secondary transmitter (ST) simultaneously sends superimposed signals to secondary receivers (SRs) (a public SR and a covert SR) via NOMA with the assistance of the UAV-RIS. Then, a UAV warden and a UAV jammer launch a cooperative attack, in which the first adversary wiretaps the signals from the ST and UAV-RIS, whereas the second interferes with the SRs to force the ST to increase its transmit power. For improved secrecy, the UAV-RIS uses its harvested energy to combat the UAV warden. For this system, the secrecy performance is evaluated on the basis of the concept of covert communication. In particular, optimization algorithms are employed to maximize the covert SR throughput under outage probability and security constraints. A deep neural network model is subsequently trained to discover the relationships between the environmental parameters and optimized parameters to enable rapid adaptation to environmental conditions.
format Article
id doaj-art-2ee782e7315f41038248cb4b1cecf9ed
institution Kabale University
issn 2644-125X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Open Journal of the Communications Society
spelling doaj-art-2ee782e7315f41038248cb4b1cecf9ed2025-08-20T03:43:55ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-0164140415510.1109/OJCOMS.2025.356576410980338Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive SystemsVan Nhan Vo0https://orcid.org/0000-0003-0753-5203Nguyen Quoc Long1Viet-Hung Dang2Tu Dac Ho3https://orcid.org/0000-0001-7215-0479Hung Tran4Symeon Chatzinotas5https://orcid.org/0000-0001-5122-0001Dinh-Hieu Tran6https://orcid.org/0000-0002-6328-3103Surasak Sanguanpong7https://orcid.org/0000-0002-7045-7394Chakchai So-In8https://orcid.org/0000-0003-1026-191XFaculty of Information Technology, Duy Tan University, Da Nang, VietnamFaculty of Information Technology, Duy Tan University, Da Nang, VietnamFaculty of Information Technology, Duy Tan University, Da Nang, VietnamDepartment of Information Security and Communication Technology, Faculty of Information Technology and Electrical Engineering, Norwegian University of Science and Technology, Trondheim, NorwayDATCOM Lab, Faculty of Data Science and Artificial Intelligence, College of Technology, National Economics University, Hanoi, VietnamInterdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Esch-sur-Alzette, LuxembourgInterdisciplinary Centre for Security, Reliability and Trust, University of Luxembourg, Esch-sur-Alzette, LuxembourgDepartment of Computer Engineering, Faculty of Engineering, Kasetsart University, Bangkok, ThailandApplied Network Technology, College of Computing, Khon Kaen University, Khon Kaen, ThailandThis paper examines a cognitive radio (CR) nonorthogonal multiple access (NOMA) system in which an unmanned aerial vehicle equipped with a reconfigurable intelligent surface (UAV-RIS) plays two roles: relaying and friendly jamming. The communication protocol has two phases. The first is an energy harvesting phase in which the UAV harvests radio frequency energy from a power beacon. In the second phase, a secondary transmitter (ST) simultaneously sends superimposed signals to secondary receivers (SRs) (a public SR and a covert SR) via NOMA with the assistance of the UAV-RIS. Then, a UAV warden and a UAV jammer launch a cooperative attack, in which the first adversary wiretaps the signals from the ST and UAV-RIS, whereas the second interferes with the SRs to force the ST to increase its transmit power. For improved secrecy, the UAV-RIS uses its harvested energy to combat the UAV warden. For this system, the secrecy performance is evaluated on the basis of the concept of covert communication. In particular, optimization algorithms are employed to maximize the covert SR throughput under outage probability and security constraints. A deep neural network model is subsequently trained to discover the relationships between the environmental parameters and optimized parameters to enable rapid adaptation to environmental conditions.https://ieeexplore.ieee.org/document/10980338/Cognitive radio (CR)nonorthogonal multiple access (NOMA)unmanned aerial vehicle (UAV)RIScovert communication
spellingShingle Van Nhan Vo
Nguyen Quoc Long
Viet-Hung Dang
Tu Dac Ho
Hung Tran
Symeon Chatzinotas
Dinh-Hieu Tran
Surasak Sanguanpong
Chakchai So-In
Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems
IEEE Open Journal of the Communications Society
Cognitive radio (CR)
nonorthogonal multiple access (NOMA)
unmanned aerial vehicle (UAV)
RIS
covert communication
title Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems
title_full Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems
title_fullStr Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems
title_full_unstemmed Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems
title_short Deep Learning-Driven Throughput Maximization in Covert Communication for UAV-RIS Cognitive Systems
title_sort deep learning driven throughput maximization in covert communication for uav ris cognitive systems
topic Cognitive radio (CR)
nonorthogonal multiple access (NOMA)
unmanned aerial vehicle (UAV)
RIS
covert communication
url https://ieeexplore.ieee.org/document/10980338/
work_keys_str_mv AT vannhanvo deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT nguyenquoclong deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT viethungdang deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT tudacho deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT hungtran deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT symeonchatzinotas deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT dinhhieutran deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT surasaksanguanpong deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems
AT chakchaisoin deeplearningdriventhroughputmaximizationincovertcommunicationforuavriscognitivesystems