Neural-Network-Based Digital Predistortion for Active Antenna Arrays under Load Modulation

Alberto Brihuega; Lauri Anttila; Mikko Valkama

doi:10.1109/LMWC.2020.3004003

Neural-Network-Based Digital Predistortion for Active Antenna Arrays under Load Modulation

Alberto Brihuega
, Lauri Anttila
, Mikko Valkama^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › Scientific › peer-review

27 Citations (Scopus)

78 Downloads (Pure)

Abstract

In this letter, we propose an efficient solution to linearize mmWave active antenna array transmitters that suffer from beam-dependent load modulation. We consider a dense neural network that is capable of modeling the correlation between the nonlinear distortion characteristics among different beams. This allows providing consistently good linearization regardless of the beamforming direction, thus avoiding the necessity of executing continuous digital predistortion parameter learning. The proposed solution is validated, conforming to 5G new radio transmit signal quality requirements, with extensive over-the-air RF measurements utilizing a state-of-the-art 64-element active antenna array operating at 28-GHz carrier frequency.

Original language	English
Pages (from-to)	843-846
Number of pages	4
Journal	IEEE Microwave and Wireless Components Letters
Volume	30
Issue number	8
DOIs	https://doi.org/10.1109/LMWC.2020.3004003
Publication status	Published - 1 Aug 2020
Publication type	A1 Journal article-refereed

Funding

Manuscript received May 8, 2020; revised June 4, 2020; accepted June 12, 2020. Date of publication July 1, 2020; date of current version August 7, 2020. This work was supported in part by the Academy of Finland under Project 304147, Project 301820, and Project 319994; in part by Nokia Bell Labs; and in part by the Tampere University Doctoral School. (Corresponding author: Mikko Valkama.) The authors are with the Department of Electrical Engineering, Tampere University, 33100 Tampere, Finland (e-mail: [email protected]). Data is available on-line at https://doi.org/10.5281/zenodo.3904473. Color versions of one or more of the figures in this letter are available online at http://ieeexplore.ieee.org. Digital Object Identifier 10.1109/LMWC.2020.3004003

Keywords

5G new radio (NR)
digital predistortion (DPD)
load modulation
mmWave
neural networks (NNs)
nonlinear distortion

Publication forum classification

Publication forum level 2

ASJC Scopus subject areas

Condensed Matter Physics
Electrical and Electronic Engineering

Access to Document

10.1109/LMWC.2020.3004003

Neural-Network-Based Digital Predistortion 2020
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 4.14 MB

http://urn.fi/URN:NBN:fi:tuni-202009307194

Cite this

@article{d0fde2bcfdfc4e5ba66579abb84130ca,

title = "Neural-Network-Based Digital Predistortion for Active Antenna Arrays under Load Modulation",

abstract = "In this letter, we propose an efficient solution to linearize mmWave active antenna array transmitters that suffer from beam-dependent load modulation. We consider a dense neural network that is capable of modeling the correlation between the nonlinear distortion characteristics among different beams. This allows providing consistently good linearization regardless of the beamforming direction, thus avoiding the necessity of executing continuous digital predistortion parameter learning. The proposed solution is validated, conforming to 5G new radio transmit signal quality requirements, with extensive over-the-air RF measurements utilizing a state-of-the-art 64-element active antenna array operating at 28-GHz carrier frequency.",

keywords = "5G new radio (NR), digital predistortion (DPD), load modulation, mmWave, neural networks (NNs), nonlinear distortion",

author = "Alberto Brihuega and Lauri Anttila and Mikko Valkama",

year = "2020",

month = aug,

day = "1",

doi = "10.1109/LMWC.2020.3004003",

language = "English",

volume = "30",

pages = "843--846",

journal = "IEEE Microwave and Wireless Components Letters",

issn = "1531-1309",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "8",

}

TY - JOUR

T1 - Neural-Network-Based Digital Predistortion for Active Antenna Arrays under Load Modulation

AU - Brihuega, Alberto

AU - Anttila, Lauri

AU - Valkama, Mikko

PY - 2020/8/1

Y1 - 2020/8/1

N2 - In this letter, we propose an efficient solution to linearize mmWave active antenna array transmitters that suffer from beam-dependent load modulation. We consider a dense neural network that is capable of modeling the correlation between the nonlinear distortion characteristics among different beams. This allows providing consistently good linearization regardless of the beamforming direction, thus avoiding the necessity of executing continuous digital predistortion parameter learning. The proposed solution is validated, conforming to 5G new radio transmit signal quality requirements, with extensive over-the-air RF measurements utilizing a state-of-the-art 64-element active antenna array operating at 28-GHz carrier frequency.

AB - In this letter, we propose an efficient solution to linearize mmWave active antenna array transmitters that suffer from beam-dependent load modulation. We consider a dense neural network that is capable of modeling the correlation between the nonlinear distortion characteristics among different beams. This allows providing consistently good linearization regardless of the beamforming direction, thus avoiding the necessity of executing continuous digital predistortion parameter learning. The proposed solution is validated, conforming to 5G new radio transmit signal quality requirements, with extensive over-the-air RF measurements utilizing a state-of-the-art 64-element active antenna array operating at 28-GHz carrier frequency.

KW - 5G new radio (NR)

KW - digital predistortion (DPD)

KW - load modulation

KW - mmWave

KW - neural networks (NNs)

KW - nonlinear distortion

U2 - 10.1109/LMWC.2020.3004003

DO - 10.1109/LMWC.2020.3004003

M3 - Article

AN - SCOPUS:85089486641

SN - 1531-1309

VL - 30

SP - 843

EP - 846

JO - IEEE Microwave and Wireless Components Letters

JF - IEEE Microwave and Wireless Components Letters

IS - 8

ER -

Neural-Network-Based Digital Predistortion for Active Antenna Arrays under Load Modulation

Abstract

Funding

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this