A Deep Q-Learning Bisection Approach for Power Allocation in Downlink NOMA Systems - Archive ouverte HAL Access content directly
Journal Articles IEEE Communications Letters Year : 2021

A Deep Q-Learning Bisection Approach for Power Allocation in Downlink NOMA Systems

(1, 2) , (1, 2) , (3, 4) , (1, 2)
1
2
3
4

Abstract

In this work, we study the weighted sum-rate maximization problem for a downlink non-orthogonal multiple access (NOMA) system. With power and data-rate constraints, this problem is generally non-convex. Therefore, a novel solution based on the deep reinforcement learning (DRL) framework is proposed for the power allocation problem. While previous work based on DRL restrict the solution to a limited set of possible power levels, the proposed DRL framework is specifically designed to find a solution with a much larger granularity, emulating a continuous power allocation. Simulation results show that the proposed power allocation method outperforms two baseline algorithms. Moreover, it achieves almost 85% of the weighted sum-rate obtained by a far more complex genetic algorithm that approaches exhaustive search in terms of performance.
Fichier principal
Vignette du fichier
Downlink_NOMA_DRL_Based_Power_Allocation.pdf (327.23 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03448296 , version 1 (09-02-2022)

Identifiers

Cite

Marie-Josepha Youssef, Charbel Abdel Nour, Xavier Lagrange, Catherine Douillard. A Deep Q-Learning Bisection Approach for Power Allocation in Downlink NOMA Systems. IEEE Communications Letters, 2021, 26 (2), pp.316-320. ⟨10.1109/LCOMM.2021.3130102⟩. ⟨hal-03448296⟩
95 View
46 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More