Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication

Amjad  Iqbal; Ala'a Al-Habashna; Gabriel Wainer; Faouzi Bouali; Gary Boudreau; Khan Wali

doi:10.1109/VTC2023-Fall60731.2023.10333558

Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication

Amjad Iqbal, Ala'a Al-Habashna, Gabriel Wainer, Faouzi Bouali, Gary Boudreau, Khan Wali

Centre for Future Transport and Cities

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

2 Citations (Scopus)

120 Downloads (Pure)

Abstract

We investigate the use of reconfigurable intelligent surfaces (RISs) in wireless networks to maximize the sum secrecy rate (i.e., the sum maximum rate that can be communicated under perfect secrecy). Specifically, we focus on a network that utilizes RIS-assisted unmanned aerial vehicles (UAVs) under imperfect channel state information (CSI). Our objective is to maximize the sum secrecy rate while dealing with the presence of multiple eavesdroppers. To achieve this, we jointly optimize the active (UAV) and passive (RIS) beamforming together with the UAV's trajectories. The formulated problem is non-convex due to the coupling of CSI with the maneuverability of the UAV. To overcome this challenge, we propose a policy-based deep reinforcement learning (DRL) approach that solves the non-convex optimization problem in a centralized fashion. Finally, simulation results show that our proposed approach significantly improves average sum secrecy rates over conventional approaches.

Original language	English
Title of host publication	2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	9798350329285
ISBN (Print)	9798350329292
DOIs	https://doi.org/10.1109/VTC2023-Fall60731.2023.10333558
Publication status	E-pub ahead of print - 11 Dec 2023
Event	98th IEEE Vehicular Technology Conference, VTC 2023-Fall - Hong Kong, China Duration: 10 Oct 2023 → 13 Oct 2023 https://events.vtsociety.org/vtc2023-fall/

Publication series

Name	2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)
Publisher	IEEE
ISSN (Print)	1090-3038
ISSN (Electronic)	2577-2465

Conference

Conference	98th IEEE Vehicular Technology Conference, VTC 2023-Fall
Abbreviated title	VTC2023-Fall
Country/Territory	China
City	Hong Kong
Period	10/10/23 → 13/10/23
Internet address	https://events.vtsociety.org/vtc2023-fall/

Bibliographical note

This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

Keywords

UAV
RIS
Eavesdropper
Secrecy rate
DRL

Access to Document

10.1109/VTC2023-Fall60731.2023.10333558

Post-PrintAccepted author manuscript, 726 KB

Cite this

Iqbal, A., Al-Habashna, A., Wainer, G., Bouali, F., Boudreau, G., & Wali, K. (2023). Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication. In 2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings (pp. 1-6). (2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)). IEEE. Advance online publication. https://doi.org/10.1109/VTC2023-Fall60731.2023.10333558

Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication. / Iqbal, Amjad ; Al-Habashna, Ala'a; Wainer, Gabriel et al.
2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings. IEEE, 2023. p. 1-6 (2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Iqbal, A, Al-Habashna, A, Wainer, G, Bouali, F, Boudreau, G & Wali, K 2023, Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication. in 2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings. 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall), IEEE, pp. 1-6, 98th IEEE Vehicular Technology Conference, VTC 2023-Fall, Hong Kong, China, 10/10/23. https://doi.org/10.1109/VTC2023-Fall60731.2023.10333558

Iqbal A, Al-Habashna A, Wainer G, Bouali F, Boudreau G, Wali K. Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication. In 2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings. IEEE. 2023. p. 1-6. (2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)). Epub 2023 Dec 11. doi: 10.1109/VTC2023-Fall60731.2023.10333558

@inproceedings{e46e847d91e342bb8a6c7368ee797626,

title = "Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication",

abstract = "We investigate the use of reconfigurable intelligent surfaces (RISs) in wireless networks to maximize the sum secrecy rate (i.e., the sum maximum rate that can be communicated under perfect secrecy). Specifically, we focus on a network that utilizes RIS-assisted unmanned aerial vehicles (UAVs) under imperfect channel state information (CSI). Our objective is to maximize the sum secrecy rate while dealing with the presence of multiple eavesdroppers. To achieve this, we jointly optimize the active (UAV) and passive (RIS) beamforming together with the UAV's trajectories. The formulated problem is non-convex due to the coupling of CSI with the maneuverability of the UAV. To overcome this challenge, we propose a policy-based deep reinforcement learning (DRL) approach that solves the non-convex optimization problem in a centralized fashion. Finally, simulation results show that our proposed approach significantly improves average sum secrecy rates over conventional approaches.",

keywords = "UAV, RIS, Eavesdropper, Secrecy rate, DRL",

author = "Amjad Iqbal and Ala'a Al-Habashna and Gabriel Wainer and Faouzi Bouali and Gary Boudreau and Khan Wali",

note = "This document is the author{\textquoteright}s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it. ; 98th IEEE Vehicular Technology Conference, VTC 2023-Fall, VTC2023-Fall ; Conference date: 10-10-2023 Through 13-10-2023",

year = "2023",

month = dec,

day = "11",

doi = "10.1109/VTC2023-Fall60731.2023.10333558",

language = "English",

isbn = "9798350329292",

series = "2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)",

publisher = "IEEE",

pages = "1--6",

booktitle = "2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings",

address = "United States",

url = "https://events.vtsociety.org/vtc2023-fall/",

}

TY - GEN

T1 - Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication

AU - Iqbal, Amjad

AU - Al-Habashna, Ala'a

AU - Wainer, Gabriel

AU - Bouali, Faouzi

AU - Boudreau, Gary

AU - Wali, Khan

N1 - This document is the author’s post-print version, incorporating any revisions agreed during the peer-review process. Some differences between the published version and this version may remain and you are advised to consult the published version if you wish to cite from it.

PY - 2023/12/11

Y1 - 2023/12/11

N2 - We investigate the use of reconfigurable intelligent surfaces (RISs) in wireless networks to maximize the sum secrecy rate (i.e., the sum maximum rate that can be communicated under perfect secrecy). Specifically, we focus on a network that utilizes RIS-assisted unmanned aerial vehicles (UAVs) under imperfect channel state information (CSI). Our objective is to maximize the sum secrecy rate while dealing with the presence of multiple eavesdroppers. To achieve this, we jointly optimize the active (UAV) and passive (RIS) beamforming together with the UAV's trajectories. The formulated problem is non-convex due to the coupling of CSI with the maneuverability of the UAV. To overcome this challenge, we propose a policy-based deep reinforcement learning (DRL) approach that solves the non-convex optimization problem in a centralized fashion. Finally, simulation results show that our proposed approach significantly improves average sum secrecy rates over conventional approaches.

AB - We investigate the use of reconfigurable intelligent surfaces (RISs) in wireless networks to maximize the sum secrecy rate (i.e., the sum maximum rate that can be communicated under perfect secrecy). Specifically, we focus on a network that utilizes RIS-assisted unmanned aerial vehicles (UAVs) under imperfect channel state information (CSI). Our objective is to maximize the sum secrecy rate while dealing with the presence of multiple eavesdroppers. To achieve this, we jointly optimize the active (UAV) and passive (RIS) beamforming together with the UAV's trajectories. The formulated problem is non-convex due to the coupling of CSI with the maneuverability of the UAV. To overcome this challenge, we propose a policy-based deep reinforcement learning (DRL) approach that solves the non-convex optimization problem in a centralized fashion. Finally, simulation results show that our proposed approach significantly improves average sum secrecy rates over conventional approaches.

KW - UAV

KW - RIS

KW - Eavesdropper

KW - Secrecy rate

KW - DRL

UR - http://www.scopus.com/inward/record.url?scp=85181174107&partnerID=8YFLogxK

U2 - 10.1109/VTC2023-Fall60731.2023.10333558

DO - 10.1109/VTC2023-Fall60731.2023.10333558

M3 - Conference proceeding

SN - 9798350329292

T3 - 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)

SP - 1

EP - 6

BT - 2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings

PB - IEEE

T2 - 98th IEEE Vehicular Technology Conference, VTC 2023-Fall

Y2 - 10 October 2023 through 13 October 2023

ER -

Deep Reinforcement Learning Based Resource Allocation for Secure RIS-aided UAV Communication

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this