Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems

Ayman Rabee; Imad Barhumi

doi:10.1109/AICT59525.2023.10313195

Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems

Ayman Rabee
, Imad Barhumi

Department of Electrical and Communication Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Nonorthogonal multiple access (NOMA) technology shows the potential for improving spectral efficiency and enables massive connectivity in future wireless networks. Unlike orthogonal schemes that require separate resources for each user, NOMA allows multiple users to share the same frequency and time resource. However, joint subchannel assignment and power allocation in multiuser uplink NOMA systems is NP-hard to solve, posing a significant challenge. In this paper, we formulate this joint problem to maximize the energy efficiency and propose a deep reinforcement learning-based approach as a solution. In this approach, we adopt the twin delayed deep deterministic algorithm for the power allocation and deep Q network for the subchannel assignment. Simulation results demonstrate that the proposed approach improves the energy efficiency performance of the multiuser uplink NOMA system and outperforms other methods.

Original language	English
Title of host publication	17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350303568
DOIs	https://doi.org/10.1109/AICT59525.2023.10313195
Publication status	Published - 2023
Event	17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Baku, Azerbaijan Duration: Oct 18 2023 → Oct 20 2023

Publication series

Name	17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings

Conference

Conference	17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023
Country/Territory	Azerbaijan
City	Baku
Period	10/18/23 → 10/20/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Nonorthogonal multiple access (NOMA)
deep Q network (DQN)
deep deterministic policy gradient (DDPG)
deep reinforcement learning (DRL)
twin-delayed DDPG (TD3)

ASJC Scopus subject areas

Information Systems
Information Systems and Management
Modelling and Simulation
Artificial Intelligence
Computer Networks and Communications
Computer Science Applications

Access to Document

10.1109/AICT59525.2023.10313195

Cite this

Rabee, A., & Barhumi, I. (2023). Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems. In 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings (17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICT59525.2023.10313195

Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems. / Rabee, Ayman; Barhumi, Imad.
17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Rabee, A & Barhumi, I 2023, Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems. in 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings. 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023, Baku, Azerbaijan, 10/18/23. https://doi.org/10.1109/AICT59525.2023.10313195

Rabee A, Barhumi I. Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems. In 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings). doi: 10.1109/AICT59525.2023.10313195

Rabee, Ayman ; Barhumi, Imad. / Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems. 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings).

@inproceedings{a3352328bd634dd7a4fc28368bd4a418,

title = "Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems",

abstract = "Nonorthogonal multiple access (NOMA) technology shows the potential for improving spectral efficiency and enables massive connectivity in future wireless networks. Unlike orthogonal schemes that require separate resources for each user, NOMA allows multiple users to share the same frequency and time resource. However, joint subchannel assignment and power allocation in multiuser uplink NOMA systems is NP-hard to solve, posing a significant challenge. In this paper, we formulate this joint problem to maximize the energy efficiency and propose a deep reinforcement learning-based approach as a solution. In this approach, we adopt the twin delayed deep deterministic algorithm for the power allocation and deep Q network for the subchannel assignment. Simulation results demonstrate that the proposed approach improves the energy efficiency performance of the multiuser uplink NOMA system and outperforms other methods.",

keywords = "Nonorthogonal multiple access (NOMA), deep Q network (DQN), deep deterministic policy gradient (DDPG), deep reinforcement learning (DRL), twin-delayed DDPG (TD3)",

author = "Ayman Rabee and Imad Barhumi",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 ; Conference date: 18-10-2023 Through 20-10-2023",

year = "2023",

doi = "10.1109/AICT59525.2023.10313195",

language = "English",

series = "17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings",

}

TY - GEN

T1 - Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems

AU - Rabee, Ayman

AU - Barhumi, Imad

PY - 2023

Y1 - 2023

N2 - Nonorthogonal multiple access (NOMA) technology shows the potential for improving spectral efficiency and enables massive connectivity in future wireless networks. Unlike orthogonal schemes that require separate resources for each user, NOMA allows multiple users to share the same frequency and time resource. However, joint subchannel assignment and power allocation in multiuser uplink NOMA systems is NP-hard to solve, posing a significant challenge. In this paper, we formulate this joint problem to maximize the energy efficiency and propose a deep reinforcement learning-based approach as a solution. In this approach, we adopt the twin delayed deep deterministic algorithm for the power allocation and deep Q network for the subchannel assignment. Simulation results demonstrate that the proposed approach improves the energy efficiency performance of the multiuser uplink NOMA system and outperforms other methods.

AB - Nonorthogonal multiple access (NOMA) technology shows the potential for improving spectral efficiency and enables massive connectivity in future wireless networks. Unlike orthogonal schemes that require separate resources for each user, NOMA allows multiple users to share the same frequency and time resource. However, joint subchannel assignment and power allocation in multiuser uplink NOMA systems is NP-hard to solve, posing a significant challenge. In this paper, we formulate this joint problem to maximize the energy efficiency and propose a deep reinforcement learning-based approach as a solution. In this approach, we adopt the twin delayed deep deterministic algorithm for the power allocation and deep Q network for the subchannel assignment. Simulation results demonstrate that the proposed approach improves the energy efficiency performance of the multiuser uplink NOMA system and outperforms other methods.

KW - Nonorthogonal multiple access (NOMA)

KW - deep Q network (DQN)

KW - deep deterministic policy gradient (DDPG)

KW - deep reinforcement learning (DRL)

KW - twin-delayed DDPG (TD3)

UR - https://www.scopus.com/pages/publications/85179517436

UR - https://www.scopus.com/pages/publications/85179517436#tab=citedBy

U2 - 10.1109/AICT59525.2023.10313195

DO - 10.1109/AICT59525.2023.10313195

M3 - Conference contribution

AN - SCOPUS:85179517436

T3 - 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings

BT - 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th IEEE International Conference on Application of Information and Communication Technologies, AICT 2023

Y2 - 18 October 2023 through 20 October 2023

ER -

Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems

Abstract

Publication series

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this