Recurrent Neural Network Equalizer to Extend Input Power Dynamic Range of SOA in 100Gb/s/λ PON

Stephen Murphy; Paul D. Townsend; Cleitus Antony

Recurrent Neural Network Equalizer to Extend Input Power Dynamic Range of SOA in 100Gb/s/λ PON

Stephen Murphy
, Paul D. Townsend
, Cleitus Antony

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

Abstract

We propose a novel equalization scheme for 100Gb/s/λ PAM4 PON based on Gated Recurrent Neural Network to increase SOA preamplifier input power dynamic range tolerance to 30 dB below hard-decision FEC BER limit of 3.8×10^-3

Original language	English
Article number	SW4E.1
Journal	Optics InfoBase Conference Papers
Publication status	Published - 2022
Event	CLEO: Science and Innovations, S and I 2022 - San Jose, United States Duration: 15 May 2022 → 20 May 2022

Cite this

@article{0369fc3c8e6a49a89777b05e1cc2a9d0,

title = "Recurrent Neural Network Equalizer to Extend Input Power Dynamic Range of SOA in 100Gb/s/λ PON",

abstract = "We propose a novel equalization scheme for 100Gb/s/λ PAM4 PON based on Gated Recurrent Neural Network to increase SOA preamplifier input power dynamic range tolerance to 30 dB below hard-decision FEC BER limit of 3.8×10-3",

author = "Stephen Murphy and Townsend, \{Paul D.\} and Cleitus Antony",

note = "Publisher Copyright: {\textcopyright} Optica Publishing Group 2022, {\textcopyright} 2022 The Author(s); CLEO: Science and Innovations, S and I 2022 ; Conference date: 15-05-2022 Through 20-05-2022",

year = "2022",

language = "English",

journal = "Optics InfoBase Conference Papers",

issn = "2162-2701",

}

TY - JOUR

T1 - Recurrent Neural Network Equalizer to Extend Input Power Dynamic Range of SOA in 100Gb/s/λ PON

AU - Murphy, Stephen

AU - Townsend, Paul D.

AU - Antony, Cleitus

PY - 2022

Y1 - 2022

N2 - We propose a novel equalization scheme for 100Gb/s/λ PAM4 PON based on Gated Recurrent Neural Network to increase SOA preamplifier input power dynamic range tolerance to 30 dB below hard-decision FEC BER limit of 3.8×10-3

AB - We propose a novel equalization scheme for 100Gb/s/λ PAM4 PON based on Gated Recurrent Neural Network to increase SOA preamplifier input power dynamic range tolerance to 30 dB below hard-decision FEC BER limit of 3.8×10-3

UR - https://www.scopus.com/pages/publications/85136794248

M3 - Article

AN - SCOPUS:85136794248

SN - 2162-2701

JO - Optics InfoBase Conference Papers

JF - Optics InfoBase Conference Papers

M1 - SW4E.1

T2 - CLEO: Science and Innovations, S and I 2022

Y2 - 15 May 2022 through 20 May 2022

ER -

Recurrent Neural Network Equalizer to Extend Input Power Dynamic Range of SOA in 100Gb/s/λ PON

Abstract

Other files and links

Fingerprint

Cite this