Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems

Abstract Millimeter-wave (mmWave) massive multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) is proven to be a primary technique for sixth-generation (6G) wireless communication networks. However, the great increase in users and antennas brings challenges for interference supp...

Full description

Saved in:
Bibliographic Details
Main Authors: Minghao Wang, Xin Liu, Fang Wang, Yang Liu, Tianshuang Qiu, Minglu Jin
Format: Article
Language:English
Published: Nature Portfolio 2024-04-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-024-59241-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850061935061499904
author Minghao Wang
Xin Liu
Fang Wang
Yang Liu
Tianshuang Qiu
Minglu Jin
author_facet Minghao Wang
Xin Liu
Fang Wang
Yang Liu
Tianshuang Qiu
Minglu Jin
author_sort Minghao Wang
collection DOAJ
description Abstract Millimeter-wave (mmWave) massive multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) is proven to be a primary technique for sixth-generation (6G) wireless communication networks. However, the great increase in users and antennas brings challenges for interference suppression and resource allocation for mmWave massive MIMO-NOMA systems. This study proposes a spectrum-efficient and fast convergence deep reinforcement learning (DRL)-based resource allocation framework to optimize user grouping and allocation of subchannel and power. First, an enhanced K-means grouping algorithm is proposed to reduce the multi-user interference and accelerate the convergence. Then, a dueling deep Q-network (DQN) structure is proposed to perform subchannel allocation, which further improves the convergence speed. Moreover, a deep deterministic policy gradient (DDPG)-based power resource allocation algorithm is designed to avoid the performance loss caused by power quantization and improve the system’s achievable sum-rate. The simulation results demonstrate that our proposed scheme outperforms other neural network-based algorithms in terms of convergence performance, and can achieve higher system capacity compared with the greedy algorithm, the random algorithm, the RNN algorithm, and the DoubleDQN algorithm.
format Article
id doaj-art-158f7248bf9049febd17dc32551cb8dd
institution DOAJ
issn 2045-2322
language English
publishDate 2024-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-158f7248bf9049febd17dc32551cb8dd2025-08-20T02:50:03ZengNature PortfolioScientific Reports2045-23222024-04-0114111810.1038/s41598-024-59241-xSpectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systemsMinghao Wang0Xin Liu1Fang Wang2Yang Liu3Tianshuang Qiu4Minglu Jin5College of Electronic Information Engineering, Inner Mongolia UniversityCollege of Electronic Information Engineering, Inner Mongolia UniversityCollege of Electronic Information Engineering, Inner Mongolia UniversityCollege of Electronic Information Engineering, Inner Mongolia UniversityFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyFaculty of Electronic Information and Electrical Engineering, Dalian University of TechnologyAbstract Millimeter-wave (mmWave) massive multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) is proven to be a primary technique for sixth-generation (6G) wireless communication networks. However, the great increase in users and antennas brings challenges for interference suppression and resource allocation for mmWave massive MIMO-NOMA systems. This study proposes a spectrum-efficient and fast convergence deep reinforcement learning (DRL)-based resource allocation framework to optimize user grouping and allocation of subchannel and power. First, an enhanced K-means grouping algorithm is proposed to reduce the multi-user interference and accelerate the convergence. Then, a dueling deep Q-network (DQN) structure is proposed to perform subchannel allocation, which further improves the convergence speed. Moreover, a deep deterministic policy gradient (DDPG)-based power resource allocation algorithm is designed to avoid the performance loss caused by power quantization and improve the system’s achievable sum-rate. The simulation results demonstrate that our proposed scheme outperforms other neural network-based algorithms in terms of convergence performance, and can achieve higher system capacity compared with the greedy algorithm, the random algorithm, the RNN algorithm, and the DoubleDQN algorithm.https://doi.org/10.1038/s41598-024-59241-x
spellingShingle Minghao Wang
Xin Liu
Fang Wang
Yang Liu
Tianshuang Qiu
Minglu Jin
Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems
Scientific Reports
title Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems
title_full Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems
title_fullStr Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems
title_full_unstemmed Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems
title_short Spectrum-efficient user grouping and resource allocation based on deep reinforcement learning for mmWave massive MIMO-NOMA systems
title_sort spectrum efficient user grouping and resource allocation based on deep reinforcement learning for mmwave massive mimo noma systems
url https://doi.org/10.1038/s41598-024-59241-x
work_keys_str_mv AT minghaowang spectrumefficientusergroupingandresourceallocationbasedondeepreinforcementlearningformmwavemassivemimonomasystems
AT xinliu spectrumefficientusergroupingandresourceallocationbasedondeepreinforcementlearningformmwavemassivemimonomasystems
AT fangwang spectrumefficientusergroupingandresourceallocationbasedondeepreinforcementlearningformmwavemassivemimonomasystems
AT yangliu spectrumefficientusergroupingandresourceallocationbasedondeepreinforcementlearningformmwavemassivemimonomasystems
AT tianshuangqiu spectrumefficientusergroupingandresourceallocationbasedondeepreinforcementlearningformmwavemassivemimonomasystems
AT minglujin spectrumefficientusergroupingandresourceallocationbasedondeepreinforcementlearningformmwavemassivemimonomasystems