Multilevel PAM with ANN equalization for an RC-LED SI-POF system

Isaac N. O. Osahon; Sujan Rajbhandari; Asim Ihsan; Jianming Tang; Wasiu O. Popoola

doi:10.1109/CCNC51644.2023.10059694

Multilevel PAM with ANN equalization for an RC-LED SI-POF system

Isaac N. O. Osahon, Sujan Rajbhandari, Asim Ihsan, Jianming Tang, Wasiu O. Popoola

Institute Of Photonics

Research output: Contribution to conference › Paper › peer-review

2 Citations (Scopus)

Abstract

In this experimental study, data transmission over step-index plastic optical fiber (SI-POF) is implemented with multilevel pulse amplitude modulation (PAM-M) scheme using a resonant cavity light emitting diode (RC-LED) as the optical transmitter. An artificial neural network (ANN) based equalizer is used in the RC-LED SI-POF system to jointly mitigate channel distortion and system non-linearities. Furthermore, the ANN equalizer's performance is compared to state-of-the-art equalizers used for the system - the Volterra equalizer and the decision feedback equalizer (DFE). The ANN equalizer offers the best bit rates compared to the others for the system with high non-linearities. For instance, at a BER of about 10 −3 , the ANN equalizer results in a bit rate of 780 Mbps, 710 Mbps, and 650 Mbps with PAM-2, PAM-4 and PAM-8 schemes, respectively. However, the Volterra equalizer results in a bit rate of 720 Mbps, 660 Mbps, and 580 Mbps with these PAM schemes, respectively. And with the DFE, the bit rates are 610 Mbps, 510 Mbps, and 120 Mbps, respectively.

Original language	English
Pages	481-484
Number of pages	4
DOIs	https://doi.org/10.1109/CCNC51644.2023.10059694
Publication status	Published - 17 Mar 2023
Event	2023 IEEE 20th Consumer Communications & Networking Conference (CCNC) - Las Vegas, United States Duration: 8 Jan 2023 → 11 Jan 2023

Conference

Conference	2023 IEEE 20th Consumer Communications & Networking Conference (CCNC)
Abbreviated title	CCNC 2023
Country/Territory	United States
City	Las Vegas
Period	8/01/23 → 11/01/23

Keywords

equalization
artificial neural network
multi-layer perceptron
plastic optical fiber communication
pulse amplitude modulation
resonant cavity light emitting diode
optical transmitters
bit rate
optical distortion
decision feedback equalizers
light emitting diodes
nonlinear systems

Access to Document

10.1109/CCNC51644.2023.10059694

Cite this

@conference{e44f1463afe14a13b25becdb3bc0f774,

title = "Multilevel PAM with ANN equalization for an RC-LED SI-POF system",

abstract = "In this experimental study, data transmission over step-index plastic optical fiber (SI-POF) is implemented with multilevel pulse amplitude modulation (PAM-M) scheme using a resonant cavity light emitting diode (RC-LED) as the optical transmitter. An artificial neural network (ANN) based equalizer is used in the RC-LED SI-POF system to jointly mitigate channel distortion and system non-linearities. Furthermore, the ANN equalizer's performance is compared to state-of-the-art equalizers used for the system - the Volterra equalizer and the decision feedback equalizer (DFE). The ANN equalizer offers the best bit rates compared to the others for the system with high non-linearities. For instance, at a BER of about 10 −3 , the ANN equalizer results in a bit rate of 780 Mbps, 710 Mbps, and 650 Mbps with PAM-2, PAM-4 and PAM-8 schemes, respectively. However, the Volterra equalizer results in a bit rate of 720 Mbps, 660 Mbps, and 580 Mbps with these PAM schemes, respectively. And with the DFE, the bit rates are 610 Mbps, 510 Mbps, and 120 Mbps, respectively.",

keywords = "equalization, artificial neural network, multi-layer perceptron, plastic optical fiber communication, pulse amplitude modulation, resonant cavity light emitting diode, optical transmitters, bit rate, optical distortion, decision feedback equalizers, light emitting diodes, nonlinear systems",

author = "Osahon, {Isaac N. O.} and Sujan Rajbhandari and Asim Ihsan and Jianming Tang and Popoola, {Wasiu O.}",

note = "{\textcopyright} Copyright 2023 IEEE - All rights reserved. I. N. O. Osahon, S. Rajbhandari, A. Ihsan, J. Tang and W. O. Popoola, {"}Multilevel PAM with ANN Equalization for an RC-LED SI-POF System,{"} 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, 2023, pp. 481-484, doi: 10.1109/CCNC51644.2023.10059694.; 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC), CCNC 2023 ; Conference date: 08-01-2023 Through 11-01-2023",

year = "2023",

month = mar,

day = "17",

doi = "10.1109/CCNC51644.2023.10059694",

language = "English",

pages = "481--484",

}

TY - CONF

T1 - Multilevel PAM with ANN equalization for an RC-LED SI-POF system

AU - Osahon, Isaac N. O.

AU - Rajbhandari, Sujan

AU - Ihsan, Asim

AU - Tang, Jianming

AU - Popoola, Wasiu O.

N1 - © Copyright 2023 IEEE - All rights reserved. I. N. O. Osahon, S. Rajbhandari, A. Ihsan, J. Tang and W. O. Popoola, "Multilevel PAM with ANN Equalization for an RC-LED SI-POF System," 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC), Las Vegas, NV, USA, 2023, pp. 481-484, doi: 10.1109/CCNC51644.2023.10059694.

PY - 2023/3/17

Y1 - 2023/3/17

N2 - In this experimental study, data transmission over step-index plastic optical fiber (SI-POF) is implemented with multilevel pulse amplitude modulation (PAM-M) scheme using a resonant cavity light emitting diode (RC-LED) as the optical transmitter. An artificial neural network (ANN) based equalizer is used in the RC-LED SI-POF system to jointly mitigate channel distortion and system non-linearities. Furthermore, the ANN equalizer's performance is compared to state-of-the-art equalizers used for the system - the Volterra equalizer and the decision feedback equalizer (DFE). The ANN equalizer offers the best bit rates compared to the others for the system with high non-linearities. For instance, at a BER of about 10 −3 , the ANN equalizer results in a bit rate of 780 Mbps, 710 Mbps, and 650 Mbps with PAM-2, PAM-4 and PAM-8 schemes, respectively. However, the Volterra equalizer results in a bit rate of 720 Mbps, 660 Mbps, and 580 Mbps with these PAM schemes, respectively. And with the DFE, the bit rates are 610 Mbps, 510 Mbps, and 120 Mbps, respectively.

AB - In this experimental study, data transmission over step-index plastic optical fiber (SI-POF) is implemented with multilevel pulse amplitude modulation (PAM-M) scheme using a resonant cavity light emitting diode (RC-LED) as the optical transmitter. An artificial neural network (ANN) based equalizer is used in the RC-LED SI-POF system to jointly mitigate channel distortion and system non-linearities. Furthermore, the ANN equalizer's performance is compared to state-of-the-art equalizers used for the system - the Volterra equalizer and the decision feedback equalizer (DFE). The ANN equalizer offers the best bit rates compared to the others for the system with high non-linearities. For instance, at a BER of about 10 −3 , the ANN equalizer results in a bit rate of 780 Mbps, 710 Mbps, and 650 Mbps with PAM-2, PAM-4 and PAM-8 schemes, respectively. However, the Volterra equalizer results in a bit rate of 720 Mbps, 660 Mbps, and 580 Mbps with these PAM schemes, respectively. And with the DFE, the bit rates are 610 Mbps, 510 Mbps, and 120 Mbps, respectively.

KW - equalization

KW - artificial neural network

KW - multi-layer perceptron

KW - plastic optical fiber communication

KW - pulse amplitude modulation

KW - resonant cavity light emitting diode

KW - optical transmitters

KW - bit rate

KW - optical distortion

KW - decision feedback equalizers

KW - light emitting diodes

KW - nonlinear systems

U2 - 10.1109/CCNC51644.2023.10059694

DO - 10.1109/CCNC51644.2023.10059694

M3 - Paper

SP - 481

EP - 484

T2 - 2023 IEEE 20th Consumer Communications & Networking Conference (CCNC)

Y2 - 8 January 2023 through 11 January 2023

ER -

Multilevel PAM with ANN equalization for an RC-LED SI-POF system

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this