TY - GEN
T1 - Twin Delayed DRL Approach for Resource Allocation in Multi-User NOMA Systems
AU - Rabee, Ayman
AU - Barhumi, Imad
N1 - Publisher Copyright:
© 2023 IEEE.
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 - http://www.scopus.com/inward/record.url?scp=85179517436&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85179517436&partnerID=8YFLogxK
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 -
