EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

Ming Sun iD, Yihe Zhong iD, Xiaoou He iD, Jie Zhang iD

Sensors · 25.04.2025 · 25 (9) · 2733

DOI: 10.3390/s25092733 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.04.2025. Verfasst von Ming Sun und 3 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Provincial Natural Science Foundation of China, Basic Research Fund for the Provincial Universities in Heilongjiang Province, Postgraduate innovative research project of Qiqihar University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismchannel allocationmulti-agent deep reinforcement learningnon-orthogonal multiple access (NOMA)power allocationunsupervised learning

Autor:innen und Institutionen

  • College of Computer and Control Engineering, Qiqihar University, Qiqihar 161006, China.

ORCID-Profile: Ming Sun, Yihe Zhong, Xiaoou He, Jie Zhang

Förderung

  • Provincial Natural Science Foundation of China
  • Basic Research Fund for the Provincial Universities in Heilongjiang Province
  • Postgraduate innovative research project of Qiqihar University
  • the Provincial Natural Science Foundation of China
  • the Basic Research Fund for the Provincial Universities in Heilongjiang Province
  • the Postgraduate Innovative Research Project of Qiqihar University

Zitieren

APA

Sun, M., Zhong, Y., He, X., & Zhang, J. (2025). Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning. Sensors, 25(9), 2733. https://doi.org/10.3390/s25092733

Vancouver

Sun M, Zhong Y, He X, Zhang J. Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning. Sensors. 2025;25(9):2733. doi:10.3390/s25092733

BibTeX
@article{Sun2025,
  author = {Sun, Ming and Zhong, Yihe and He, Xiaoou and Zhang, Jie},
  title = {Channel and Power Allocation for Multi-Cell NOMA Using Multi-Agent Deep Reinforcement Learning and Unsupervised Learning},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {9},
  pages = {2733},
  doi = {10.3390/s25092733}
}
Kostenlos starten →