EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Intelligent Analog Beam Selection and Beamspace Channel Tracking in THz Massive MIMO With Lens Antenna Array

Hosein Zarini, Mohammad Robat Mili, Mehdi Rasti, Sergey Andreev, Pedro H. J. Nardelli, Mehdi Bennis

IEEE Transactions on Cognitive Communications and Networking · 2023-06 · 9 (3) · 629-646

DOI: 10.1109/tccn.2023.3247756 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2023-06. Verfasst von Hosein Zarini und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Academy of Finland, Jane and Aatos Erkko Foundation via STREAM project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Beamspace multiple-input-multiple-output (MIMO) as a green technology can efficiently substitute for the conventional massive MIMO, provided that the beamspace channel is acquired precisely. The prior efforts in this area of study, especially the learning-driven ones, however, indicate remarkable performance losses owing to a lack of generalization. In this paper, we propose a modified non-linear auto-regressive exogenous (NARX) model for tracking and predicting the beamspace channel over the sequences of time. Benefiting from bounded generalization error, fast convergence, limited prediction variance, and negligible performance loss, the proposed scheme achieves up to 15% spectral efficiency (SE) gain over its counterparts. We further improve this performance by means of an ensemble learning technique for simultaneously training multiple NARX modules in parallel, thus leading to a 23% SE gain. Relying on the predicted beamspace channel, we propose a beamspace analog beam selection technique through fine-tuning the architecture of a pre-trained off-the-shelf GoogleNet, which brings up to 21% SE gain over similar baselines. With the aid of an ensemble learning technique, it is further indicated numerically that up to 34% SE improvement can be achieved, as compared to the counterparts.

Förderung

  • Academy of Finland
  • Jane and Aatos Erkko Foundation via STREAM project

Zitieren

APA

Zarini, H., Mili, M. R., Rasti, M., Andreev, S., Nardelli, P. H. J., & Bennis, M. (2023). Intelligent Analog Beam Selection and Beamspace Channel Tracking in THz Massive MIMO With Lens Antenna Array. IEEE Transactions on Cognitive Communications and Networking, 9(3), 629-646. https://doi.org/10.1109/tccn.2023.3247756

Vancouver

Zarini H, Mili MR, Rasti M, Andreev S, Nardelli PHJ, Bennis M. Intelligent Analog Beam Selection and Beamspace Channel Tracking in THz Massive MIMO With Lens Antenna Array. IEEE Transactions on Cognitive Communications and Networking. 2023;9(3):629-646. doi:10.1109/tccn.2023.3247756

BibTeX
@article{Zarini2023,
  author = {Zarini, Hosein and Mili, Mohammad Robat and Rasti, Mehdi and Andreev, Sergey and Nardelli, Pedro H. J. and Bennis, Mehdi},
  title = {Intelligent Analog Beam Selection and Beamspace Channel Tracking in THz Massive MIMO With Lens Antenna Array},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2023},
  volume = {9},
  number = {3},
  pages = {629--646},
  doi = {10.1109/tccn.2023.3247756}
}
Kostenlos starten →