Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning

Among the 5G and anticipated 6G technologies, non-orthogonal multiple access (NOMA) has attracted considerable attention due to its notable advantages in data throughput. Nevertheless, it is challenging to find the near-optimal allocation of the channel and power resources to maximize the performanc...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming Sun, Yihe Zhong, Xiaoou He, Jie Zhang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312799582322688
author Ming Sun
Yihe Zhong
Xiaoou He
Jie Zhang
author_facet Ming Sun
Yihe Zhong
Xiaoou He
Jie Zhang
author_sort Ming Sun
collection DOAJ
description Among the 5G and anticipated 6G technologies, non-orthogonal multiple access (NOMA) has attracted considerable attention due to its notable advantages in data throughput. Nevertheless, it is challenging to find the near-optimal allocation of the channel and power resources to maximize the performance of the multi-cell NOMA system. In addition, due to the complex and dynamically changing wireless communication environment and the lack of the near-optimal labels, conventional supervised learning methods cannot be directly applied. To address these challenges, this paper proposes a framework of MDRL-UL that integrates the multi-agent deep reinforcement learning with the unsupervised learning to allocate the channel and power resources in a near-optimal manner. In the framework, a multi-agent deep reinforcement learning neural network (MDRLNN) is proposed for channel allocation, while an attention-based unsupervised learning neural network (ULNN) is proposed for power allocation. Furthermore, the joint action (JA) derived from the MDRLNN for channel allocation is used as a representation to be fed into the ULNN for power allocation. In order to maximize the energy efficiency of the multi-cell NOMA system, the expectation of the energy efficiency is used to train both the MDRLNN and the ULNN. Simulation results indicate that the proposed MDRL-UL can achieve higher energy efficiency and transmission rates than other algorithms.
format Article
id doaj-art-20a343e892df4941922aec50bc84d31d
institution Kabale University
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-20a343e892df4941922aec50bc84d31d2025-08-20T03:52:57ZengMDPI AGSensors1424-82202025-04-01259273310.3390/s25092733Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised LearningMing Sun0Yihe Zhong1Xiaoou He2Jie Zhang3College of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, ChinaCollege of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, ChinaCollege of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, ChinaCollege of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, ChinaAmong the 5G and anticipated 6G technologies, non-orthogonal multiple access (NOMA) has attracted considerable attention due to its notable advantages in data throughput. Nevertheless, it is challenging to find the near-optimal allocation of the channel and power resources to maximize the performance of the multi-cell NOMA system. In addition, due to the complex and dynamically changing wireless communication environment and the lack of the near-optimal labels, conventional supervised learning methods cannot be directly applied. To address these challenges, this paper proposes a framework of MDRL-UL that integrates the multi-agent deep reinforcement learning with the unsupervised learning to allocate the channel and power resources in a near-optimal manner. In the framework, a multi-agent deep reinforcement learning neural network (MDRLNN) is proposed for channel allocation, while an attention-based unsupervised learning neural network (ULNN) is proposed for power allocation. Furthermore, the joint action (JA) derived from the MDRLNN for channel allocation is used as a representation to be fed into the ULNN for power allocation. In order to maximize the energy efficiency of the multi-cell NOMA system, the expectation of the energy efficiency is used to train both the MDRLNN and the ULNN. Simulation results indicate that the proposed MDRL-UL can achieve higher energy efficiency and transmission rates than other algorithms.https://www.mdpi.com/1424-8220/25/9/2733non-orthogonal multiple access (NOMA)channel allocationpower allocationmulti-agent deep reinforcement learningunsupervised learningattention mechanism
spellingShingle Ming Sun
Yihe Zhong
Xiaoou He
Jie Zhang
Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning
Sensors
non-orthogonal multiple access (NOMA)
channel allocation
power allocation
multi-agent deep reinforcement learning
unsupervised learning
attention mechanism
title Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning
title_full Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning
title_fullStr Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning
title_full_unstemmed Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning
title_short Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning
title_sort channel and power allocation for multi cell noma using multi agent deep reinforcement learning and unsupervised learning
topic non-orthogonal multiple access (NOMA)
channel allocation
power allocation
multi-agent deep reinforcement learning
unsupervised learning
attention mechanism
url https://www.mdpi.com/1424-8220/25/9/2733
work_keys_str_mv AT mingsun channelandpowerallocationformulticellnomausingmultiagentdeepreinforcementlearningandunsupervisedlearning
AT yihezhong channelandpowerallocationformulticellnomausingmultiagentdeepreinforcementlearningandunsupervisedlearning
AT xiaoouhe channelandpowerallocationformulticellnomausingmultiagentdeepreinforcementlearningandunsupervisedlearning
AT jiezhang channelandpowerallocationformulticellnomausingmultiagentdeepreinforcementlearningandunsupervisedlearning