EUVIMEDEUVIMED entdecken
Crossref

Scenario-Adaptive Meta-Learning for mmWave Beam Alignment

Ziyi Xu, Shuoyao Wang, Ying-Jun Angela Zhang

IEEE Transactions on Wireless Communications · 2025-04 · 24 (4) · 3192-3208

DOI: 10.1109/twc.2025.3528647 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2025-04. Verfasst von Ziyi Xu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: General Research Fund from the Research Grants Council (RGC) of Hong Kong, Area of Excellence Scheme Grant from the RGC of Hong Kong, NSFC/RGC Collaborative Research Scheme from the RGC of Hong Kong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In millimeter wave communication systems, achieving high-quality data transmission demands efficient and rapid beam alignment. Conventional deep learning-based methods, although promising, often rely on the assumption that training and testing channels share identical distribution. This assumption may not hold in practical settings, potentially leading to significant performance degradation when the deployment environment changes. To address this issue, we introduce SAMBA, a novel meta-learning-based approach for adaptive beam alignment without requiring Channel State Information (CSI). SAMBA enables swift adaptation to unknown scenarios using a minimal set of newly labeled data. Specifically, we adopt a probing beam-search strategy to obviate the need for CSI. Furthermore, we employ Model-Agnostic Meta-Learning (MAML) for parameter pre-training and fine-tuning to enhance our model’s adaptability. Confronted with the challenge of numerous beam candidates in the narrow beam selection problem, which complicates the straightforward replication of MAML, we develop a novel training task generation strategy. In our experimental assessments, we subjected SAMBA to a wide range of challenging scenarios using ray-tracing simulations. These scenarios encompassed various frequency bands, distinct base station layouts, and outdoor-to-indoor transitions. Our results demonstrate that SAMBA consistently outperforms learning-based baseline models, showcasing its superior domain adaptation capabilities in dynamic and diverse channel settings.

Förderung

  • General Research Fund from the Research Grants Council (RGC) of Hong Kong
  • Area of Excellence Scheme Grant from the RGC of Hong Kong
  • NSFC/RGC Collaborative Research Scheme from the RGC of Hong Kong
  • National Natural Science Foundation of China
  • Basic and Applied Basic Research Foundation of Guangdong Province

Zitieren

APA

Xu, Z., Wang, S., & Zhang, Y. A. (2025). Scenario-Adaptive Meta-Learning for mmWave Beam Alignment. IEEE Transactions on Wireless Communications, 24(4), 3192-3208. https://doi.org/10.1109/twc.2025.3528647

Vancouver

Xu Z, Wang S, Zhang YA. Scenario-Adaptive Meta-Learning for mmWave Beam Alignment. IEEE Transactions on Wireless Communications. 2025;24(4):3192-3208. doi:10.1109/twc.2025.3528647

BibTeX
@article{Xu2025,
  author = {Xu, Ziyi and Wang, Shuoyao and Zhang, Ying-Jun Angela},
  title = {Scenario-Adaptive Meta-Learning for mmWave Beam Alignment},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2025},
  volume = {24},
  number = {4},
  pages = {3192--3208},
  doi = {10.1109/twc.2025.3528647}
}
Kostenlos starten →