University of Oulu

H. Zarini, M. R. Mili, M. Rasti, S. Andreev, P. H. J. Nardelli and M. Bennis, "Intelligent Analog Beam Selection and Beamspace Channel Tracking in THz Massive MIMO With Lens Antenna Array," in IEEE Transactions on Cognitive Communications and Networking, vol. 9, no. 3, pp. 629-646, June 2023, doi: 10.1109/TCCN.2023.3247756.

Intelligent analog beam selection and beamspace channel tracking in THz massive MIMO with lens antenna array

Saved in:
Author: Zarini, Hosein1; Mili, Mohammad Robat2; Rasti, Mehdi3;
Organizations: 1Department of Computer Engineering, Sharif University of Technology, Tehran, Iran
2Pasargad Institute for Advanced Innovative Solutions, Tehran, Iran
3Center for Wireless Communications and the Water, Energy and Environmental Engineering Research Unit (WE3), University of Oulu, Oulu, Finland
4Faculty of Information Technology and Communication Sciences, Tampere University, Tampere, Finland
5Department of Electrical Engineering, School of Energy Systems, Lappeenranta-Lahti University of Technology, Lappeenranta, Finland
6Center for Wireless Communications, University of Oulu, Oulu, Finland
Format: article
Version: published version
Access: open
Online Access: PDF Full Text (PDF, 5.5 MB)
Persistent link:
Language: English
Published: IEEE Communications Society, 2023
Publish Date: 2023-08-14


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.

see all

Series: IEEE transactions on cognitive communications and networking
ISSN: 2372-2045
ISSN-E: 2332-7731
ISSN-L: 2372-2045
Volume: 9
Issue: 3
Pages: 629 - 646
DOI: 10.1109/TCCN.2023.3247756
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: This paper is supported in part by the (1) Academy of Finland via: (a) Profi6 336449, (b) FIREMAN consortium n.326270 as part of CHIST-ERA-17-BDSI-003, (c) EnergyNet Fellowship n.321265/n.328869/n.352654, (d) X-SDEN project n.349965, (e) projects RADIANT, IDEA-MILL, and SOLID; and (2) Jane and Aatos Erkko Foundation via STREAM project.
Copyright information: This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. For more information, see