EUVIMEDEUVIMED entdecken
Crossref

A Collaborative Multi-Agent Deep Reinforcement Learning-Based Wireless Power Allocation With Centralized Training and Decentralized Execution

Amna Kopic, Erma Perenda, Haris Gacanin

IEEE Transactions on Communications · 2024-11 · 72 (11) · 7006-7016

DOI: 10.1109/tcomm.2024.3409530 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2024-11. Verfasst von Amna Kopic und 2 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref). Gefördert von: German Federal Ministry of Education and Research (BMBF) in the course of the 6GEM research hub.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Despite the success of Deep Reinforcement Learning (DRL) in radio-resource management within multi-cell wireless networks, applying it to power allocation in ultra-dense 5G and beyond networks poses challenges. While existing multi-agent DRL-based methods often adopt a fully centralized approach, they often overlook communication overhead costs. In this paper, we model a multi-cell network as a collaborative multi-agent DRL system, implementing a centralized training-decentralized execution approach for accurate and real-time decision-making, thereby eliminating communication overhead during execution. We carefully design the DRL agents’ input observations, actions, and rewards to address potential impractical power allocation policies in multi-carrier systems and ensure strict compliance with transmit power constraints. Through extensive simulations, we assess the sensitivity of the proposed DRL-based power allocation to various exploration methods and system parameters. Results indicate superior performance of DRL-based power allocation with continuous action space in complex network environments. Conversely, simpler network settings with fewer subcarriers and users require fewer power allocation actions, ensuring rapid convergence. By leveraging a fast exploration rate, DRL-based power allocation with discrete action space outperforms conventional algorithms, achieving a 36% relative sum rate increase within 60,000 training episodes.

Förderung

  • German Federal Ministry of Education and Research (BMBF) in the course of the 6GEM research hub

Zitieren

APA

Kopic, A., Perenda, E., & Gacanin, H. (2024). A Collaborative Multi-Agent Deep Reinforcement Learning-Based Wireless Power Allocation With Centralized Training and Decentralized Execution. IEEE Transactions on Communications, 72(11), 7006-7016. https://doi.org/10.1109/tcomm.2024.3409530

Vancouver

Kopic A, Perenda E, Gacanin H. A Collaborative Multi-Agent Deep Reinforcement Learning-Based Wireless Power Allocation With Centralized Training and Decentralized Execution. IEEE Transactions on Communications. 2024;72(11):7006-7016. doi:10.1109/tcomm.2024.3409530

BibTeX
@article{Kopic2024,
  author = {Kopic, Amna and Perenda, Erma and Gacanin, Haris},
  title = {A Collaborative Multi-Agent Deep Reinforcement Learning-Based Wireless Power Allocation With Centralized Training and Decentralized Execution},
  journal = {IEEE Transactions on Communications},
  year = {2024},
  volume = {72},
  number = {11},
  pages = {7006--7016},
  doi = {10.1109/tcomm.2024.3409530}
}
Kostenlos starten →