Mixture of Experts Neural Network for Modeling of Power Amplifiers

Arne Fischer-Bühner; Alberto Brihuega; Lauri Anttila; Manil Dev Gomony; Mikko Valkama

doi:10.1109/IMS37962.2022.9865530

Mixture of Experts Neural Network for Modeling of Power Amplifiers

Arne Fischer-Bühner
, Alberto Brihuega
, Lauri Anttila
, Manil Dev Gomony
, Mikko Valkama

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

13 Citations (Scopus)

111 Downloads (Pure)

Abstract

A new Mixture of Experts Neural Network (ME-NN) approach is described and proposed for modeling of nonlinear RF power amplifiers (PAs). The proposed ME-NN is compared with various piece-wise polynomial models and the time-delay neural network (TDNN) regarding their ability to scale in terms of modeling accuracy and parameter count. To this end, measurements with GaN Doherty PA at 1.8 GHz and a load modulated balanced (LMBA) PA operating at 2.1 GHz with strong nonlinear behavior and dynamics are employed, assessing the potential benefits of ME-NN over the existing models. Implementation-related advantages of the proposed ME-NN over TDNNs at increasing network sizes are furthermore discussed. The measurement results show that the ME-NN approach offers increased modeling accuracy, particularly in the LMBA PA case, compared to the existing reference methods.

Original language	English
Title of host publication	2022 IEEE/MTT-S International Microwave Symposium, IMS 2022
Publisher	IEEE
Pages	510-513
Number of pages	4
ISBN (Electronic)	9781665496131
ISBN (Print)	9781665496148
DOIs	https://doi.org/10.1109/IMS37962.2022.9865530
Publication status	Published - 2022
Publication type	A4 Article in conference proceedings
Event	IEEE/MTT-S International Microwave Symposium - Denver, United States Duration: 19 Jun 2022 → 24 Jun 2022

Publication series

Name	IEEE MTT-S International Microwave Symposium Digest
ISSN (Print)	0149-645X
ISSN (Electronic)	2576-7216

Conference

Conference	IEEE/MTT-S International Microwave Symposium
Country/Territory	United States
City	Denver
Period	19/06/22 → 24/06/22

Funding

This work has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 860921. The work was also supported by the Academy of Finland under the grants #319994, #338224, and #332361 ACKNOWLEDGMENT This work has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No. 860921. The work was also supported by the Academy of Finland under the grants #319994, #338224, and #332361.

Keywords

5G and beyond
behavioral modeling
digital predistortion
neural network
nonlinear distortion
power amplifier

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Radiation
Condensed Matter Physics
Electrical and Electronic Engineering

Access to Document

10.1109/IMS37962.2022.9865530

Mixture of Experts Neural Network
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 1.08 MBLicence: Unspecified

https://urn.fi/URN:NBN:fi:tuni-202210207708Licence: Unspecified

Cite this

@inproceedings{b97a5c0e7291408f887959af927fc9e8,

title = "Mixture of Experts Neural Network for Modeling of Power Amplifiers",

abstract = "A new Mixture of Experts Neural Network (ME-NN) approach is described and proposed for modeling of nonlinear RF power amplifiers (PAs). The proposed ME-NN is compared with various piece-wise polynomial models and the time-delay neural network (TDNN) regarding their ability to scale in terms of modeling accuracy and parameter count. To this end, measurements with GaN Doherty PA at 1.8 GHz and a load modulated balanced (LMBA) PA operating at 2.1 GHz with strong nonlinear behavior and dynamics are employed, assessing the potential benefits of ME-NN over the existing models. Implementation-related advantages of the proposed ME-NN over TDNNs at increasing network sizes are furthermore discussed. The measurement results show that the ME-NN approach offers increased modeling accuracy, particularly in the LMBA PA case, compared to the existing reference methods.",

keywords = "5G and beyond, behavioral modeling, digital predistortion, neural network, nonlinear distortion, power amplifier",

author = "Arne Fischer-B{\"u}hner and Alberto Brihuega and Lauri Anttila and Gomony, \{Manil Dev\} and Mikko Valkama",

note = "Funding Information: This work has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 860921. The work was also supported by the Academy of Finland under the grants \#319994, \#338224, and \#332361 Publisher Copyright: {\textcopyright} 2022 IEEE. JUFOID=70577; IEEE/MTT-S International Microwave Symposium ; Conference date: 19-06-2022 Through 24-06-2022",

year = "2022",

doi = "10.1109/IMS37962.2022.9865530",

language = "English",

isbn = "9781665496148",

series = "IEEE MTT-S International Microwave Symposium Digest",

publisher = "IEEE",

pages = "510--513",

booktitle = "2022 IEEE/MTT-S International Microwave Symposium, IMS 2022",

address = "United States",

}

Fischer-Bühner, A, Brihuega, A, Anttila, L, Gomony, MD & Valkama, M 2022, Mixture of Experts Neural Network for Modeling of Power Amplifiers. in 2022 IEEE/MTT-S International Microwave Symposium, IMS 2022. IEEE MTT-S International Microwave Symposium Digest, IEEE, pp. 510-513, IEEE/MTT-S International Microwave Symposium, Denver, United States, 19/06/22. https://doi.org/10.1109/IMS37962.2022.9865530

Mixture of Experts Neural Network for Modeling of Power Amplifiers. / Fischer-Bühner, Arne; Brihuega, Alberto; Anttila, Lauri et al.
2022 IEEE/MTT-S International Microwave Symposium, IMS 2022. IEEE, 2022. p. 510-513 (IEEE MTT-S International Microwave Symposium Digest).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Mixture of Experts Neural Network for Modeling of Power Amplifiers

AU - Fischer-Bühner, Arne

AU - Brihuega, Alberto

AU - Anttila, Lauri

AU - Gomony, Manil Dev

AU - Valkama, Mikko

N1 - Funding Information: This work has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No. 860921. The work was also supported by the Academy of Finland under the grants #319994, #338224, and #332361 Publisher Copyright: © 2022 IEEE. JUFOID=70577

PY - 2022

Y1 - 2022

N2 - A new Mixture of Experts Neural Network (ME-NN) approach is described and proposed for modeling of nonlinear RF power amplifiers (PAs). The proposed ME-NN is compared with various piece-wise polynomial models and the time-delay neural network (TDNN) regarding their ability to scale in terms of modeling accuracy and parameter count. To this end, measurements with GaN Doherty PA at 1.8 GHz and a load modulated balanced (LMBA) PA operating at 2.1 GHz with strong nonlinear behavior and dynamics are employed, assessing the potential benefits of ME-NN over the existing models. Implementation-related advantages of the proposed ME-NN over TDNNs at increasing network sizes are furthermore discussed. The measurement results show that the ME-NN approach offers increased modeling accuracy, particularly in the LMBA PA case, compared to the existing reference methods.

AB - A new Mixture of Experts Neural Network (ME-NN) approach is described and proposed for modeling of nonlinear RF power amplifiers (PAs). The proposed ME-NN is compared with various piece-wise polynomial models and the time-delay neural network (TDNN) regarding their ability to scale in terms of modeling accuracy and parameter count. To this end, measurements with GaN Doherty PA at 1.8 GHz and a load modulated balanced (LMBA) PA operating at 2.1 GHz with strong nonlinear behavior and dynamics are employed, assessing the potential benefits of ME-NN over the existing models. Implementation-related advantages of the proposed ME-NN over TDNNs at increasing network sizes are furthermore discussed. The measurement results show that the ME-NN approach offers increased modeling accuracy, particularly in the LMBA PA case, compared to the existing reference methods.

KW - 5G and beyond

KW - behavioral modeling

KW - digital predistortion

KW - neural network

KW - nonlinear distortion

KW - power amplifier

U2 - 10.1109/IMS37962.2022.9865530

DO - 10.1109/IMS37962.2022.9865530

M3 - Conference contribution

AN - SCOPUS:85137975750

SN - 9781665496148

T3 - IEEE MTT-S International Microwave Symposium Digest

SP - 510

EP - 513

BT - 2022 IEEE/MTT-S International Microwave Symposium, IMS 2022

PB - IEEE

T2 - IEEE/MTT-S International Microwave Symposium

Y2 - 19 June 2022 through 24 June 2022

ER -

Mixture of Experts Neural Network for Modeling of Power Amplifiers

Abstract

Publication series

Conference

Funding

Keywords

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this