EUVIMEDEUVIMED entdecken
Crossref

Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access

Hao-Hsuan Chang, Yifei Song, Thinh T. Doan, Lingjia Liu

IEEE Transactions on Wireless Communications · 2023-08 · 22 (8) · 5337-5348

DOI: 10.1109/twc.2022.3233436 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2023-08. Verfasst von Hao-Hsuan Chang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 43-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: U.S. National Science Foundation, Commonwealth Cyber Initiative, an Investment in the Advancement of Cyber Research and Development, Innovation, and Workforce Development.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dynamic spectrum access (DSA) has been introduced as a promising technology that allows a secondary system to access the licensed spectrum of the primary system to improve spectrum utilization. In this paper, we introduce Fed-MADRL by incorporating federated learning (FL) and multi-agent deep reinforcement learning (MADRL) to design a collaborative DSA strategy. Our Fed-MADRL scheme employs FL to enable multiple users to collaboratively optimize the system goal without sharing their training data. By keeping all the training data at the user end, FL improves the communication efficiency and strengthens user data privacy. To further reduce the communication overheads, each user only shares quantized information. We provide the convergence analysis to characterize the trade-off between the communication efficiency and the system performance. In particular, we show that the introduced method converges at a rate $\mathcal {O}(1/K^{1/4})$ , where $K$ is the number of FL iterations. To the best of our knowledge, Fed-MADRL is the first work that utilizes FL in DSA networks under quantized communication. Performance evaluation results show that the introduced Fed-MADRL method outperforms the independent learning method and achieves comparable performance with the centralized MADRL method, which requires much higher communication overheads.

Förderung

  • U.S. National Science Foundation
  • Commonwealth Cyber Initiative, an Investment in the Advancement of Cyber Research and Development, Innovation, and Workforce Development

Zitieren

APA

Chang, H., Song, Y., Doan, T. T., & Liu, L. (2023). Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access. IEEE Transactions on Wireless Communications, 22(8), 5337-5348. https://doi.org/10.1109/twc.2022.3233436

Vancouver

Chang H, Song Y, Doan TT, Liu L. Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access. IEEE Transactions on Wireless Communications. 2023;22(8):5337-5348. doi:10.1109/twc.2022.3233436

BibTeX
@article{Chang2023,
  author = {Chang, Hao-Hsuan and Song, Yifei and Doan, Thinh T. and Liu, Lingjia},
  title = {Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2023},
  volume = {22},
  number = {8},
  pages = {5337--5348},
  doi = {10.1109/twc.2022.3233436}
}
Kostenlos starten →