Neural-network-based pre-distortion method to compensate for low resolution DAC nonlinearity

Mahmood Abu-Romoh; Stylianos Sygletos; Ian D. Phillips; Wladek Forysiak

doi:10.1049/cp.2019.0971

Neural-network-based pre-distortion method to compensate for low resolution DAC nonlinearity

Mahmood Abu-Romoh^*, Stylianos Sygletos, Ian D. Phillips, Wladek Forysiak

^*Corresponding author for this work

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

We evaluate the effect of digital to analogue converters (DACs) nonlinearity in transceivers based on low resolution DACs. A pre-distortion technique based on indirect learning neural networks is proposed which shows a 3.8dB improvement with high nonlinearity for 32Gbaud 64-QAM.

Original language	English
Title of host publication	IET Conference Publications
Publisher	IET
Number of pages	4
Edition	CP765
ISBN (Electronic)	9781839530074, 9781839530661, 9781839530883, 9781839530890, 9781839531071, 9781839531088, 9781839531255, 9781839531705, 9781839531859
DOIs	https://doi.org/10.1049/cp.2019.0971
Publication status	Published - 22 Sept 2019
Event	45th European Conference on Optical Communication, ECOC 2019 - Dublin, Ireland Duration: 22 Sept 2019 → 26 Sept 2019

Publication series

Name	IET Conference Publications
Number	CP765
Volume	2019

Conference

Conference	45th European Conference on Optical Communication, ECOC 2019
Country/Territory	Ireland
City	Dublin
Period	22/09/19 → 26/09/19

Bibliographical note

Publisher Copyright:
© 2019 Institution of Engineering and Technology. All rights reserved.

Keywords

Artificial Neural Networks
Data Centers
Digital Analog-Conversion
Optical Transmitters
WDM Networks

Access to Document

10.1049/cp.2019.0971

Cite this

@inproceedings{dcf76ce509eb4f1394b49e03ea8878d5,

title = "Neural-network-based pre-distortion method to compensate for low resolution DAC nonlinearity",

abstract = "We evaluate the effect of digital to analogue converters (DACs) nonlinearity in transceivers based on low resolution DACs. A pre-distortion technique based on indirect learning neural networks is proposed which shows a 3.8dB improvement with high nonlinearity for 32Gbaud 64-QAM.",

keywords = "Artificial Neural Networks, Data Centers, Digital Analog-Conversion, Optical Transmitters, WDM Networks",

author = "Mahmood Abu-Romoh and Stylianos Sygletos and Phillips, {Ian D.} and Wladek Forysiak",

note = "Publisher Copyright: {\textcopyright} 2019 Institution of Engineering and Technology. All rights reserved.; 45th European Conference on Optical Communication, ECOC 2019 ; Conference date: 22-09-2019 Through 26-09-2019",

year = "2019",

month = sep,

day = "22",

doi = "10.1049/cp.2019.0971",

language = "English",

series = "IET Conference Publications",

publisher = "IET",

number = "CP765",

booktitle = "IET Conference Publications",

address = "United Kingdom",

edition = "CP765",

}

Abu-Romoh, M, Sygletos, S , Phillips, ID & Forysiak, W 2019, Neural-network-based pre-distortion method to compensate for low resolution DAC nonlinearity. in IET Conference Publications. CP765 edn, IET Conference Publications, no. CP765, vol. 2019, IET, 45th European Conference on Optical Communication, ECOC 2019, Dublin, Ireland, 22/09/19. https://doi.org/10.1049/cp.2019.0971

TY - GEN

T1 - Neural-network-based pre-distortion method to compensate for low resolution DAC nonlinearity

AU - Abu-Romoh, Mahmood

AU - Sygletos, Stylianos

AU - Phillips, Ian D.

AU - Forysiak, Wladek

PY - 2019/9/22

Y1 - 2019/9/22

N2 - We evaluate the effect of digital to analogue converters (DACs) nonlinearity in transceivers based on low resolution DACs. A pre-distortion technique based on indirect learning neural networks is proposed which shows a 3.8dB improvement with high nonlinearity for 32Gbaud 64-QAM.

AB - We evaluate the effect of digital to analogue converters (DACs) nonlinearity in transceivers based on low resolution DACs. A pre-distortion technique based on indirect learning neural networks is proposed which shows a 3.8dB improvement with high nonlinearity for 32Gbaud 64-QAM.

KW - Artificial Neural Networks

KW - Data Centers

KW - Digital Analog-Conversion

KW - Optical Transmitters

KW - WDM Networks

UR - http://www.scopus.com/inward/record.url?scp=85086891178&partnerID=8YFLogxK

UR - https://ieeexplore.ieee.org/document/9125699

U2 - 10.1049/cp.2019.0971

DO - 10.1049/cp.2019.0971

M3 - Conference publication

AN - SCOPUS:85086891178

T3 - IET Conference Publications

BT - IET Conference Publications

PB - IET

T2 - 45th European Conference on Optical Communication, ECOC 2019

Y2 - 22 September 2019 through 26 September 2019

ER -

Neural-network-based pre-distortion method to compensate for low resolution DAC nonlinearity

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this