Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation

This paper proposes an accuracy enhancement method for fiber-longitudinal power profile estimation (PPE) based on convolutional neural networks (CNN). Two types of CNNs are designed. The first network treats different polarization streams identically and is denoted as CNN. The second network conside...

Full description

Saved in:
Bibliographic Details
Main Authors: Daobin Wang, Kun Wen, Tiantian Bai, Ruiyang Xia, Zanshan Zhao, Guanjun Gao
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/12/3/271
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850279669291548672
author Daobin Wang
Kun Wen
Tiantian Bai
Ruiyang Xia
Zanshan Zhao
Guanjun Gao
author_facet Daobin Wang
Kun Wen
Tiantian Bai
Ruiyang Xia
Zanshan Zhao
Guanjun Gao
author_sort Daobin Wang
collection DOAJ
description This paper proposes an accuracy enhancement method for fiber-longitudinal power profile estimation (PPE) based on convolutional neural networks (CNN). Two types of CNNs are designed. The first network treats different polarization streams identically and is denoted as CNN. The second network considers the difference between the contributions of different polarization streams to the nonlinear phase shift and is denoted as enhanced CNN (ECNN). The numerical simulation results confirm the effectiveness of the method for a 64 Gbaud/s quadrature phase-shift keying (QPSK) polarization-division-multiplexed (PDM) coherent optical communication system with a fiber length of 320 km. The effects of finite impulse response (FIR) filter length, power into the fiber, and polarization mode dispersion on the PPE accuracy are examined. Finally, the results of the proposed method are monitored in the presence of several simultaneous power attenuation anomalies in the fiber optic link. It is found that the accuracy of the PPE substantially improves after using the proposed method, achieving a relative gain of up to 71%. When the modulation format is changed from QPSK to 16-ary quadrature amplitude modulation (16-QAM), and the fiber length is increased from 360 km to 480 km, the proposed method is still effective. This work provides a feasible solution for implementing fiber-longitudinal PPE, enabling significantly improved estimation accuracy in practical applications.
format Article
id doaj-art-ac842bd6765e407cb2c3dc01d5192ad2
institution OA Journals
issn 2304-6732
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj-art-ac842bd6765e407cb2c3dc01d5192ad22025-08-20T01:49:01ZengMDPI AGPhotonics2304-67322025-03-0112327110.3390/photonics12030271Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile EstimationDaobin Wang0Kun Wen1Tiantian Bai2Ruiyang Xia3Zanshan Zhao4Guanjun Gao5School of Science, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Science, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Science, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Science, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaSchool of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, ChinaThis paper proposes an accuracy enhancement method for fiber-longitudinal power profile estimation (PPE) based on convolutional neural networks (CNN). Two types of CNNs are designed. The first network treats different polarization streams identically and is denoted as CNN. The second network considers the difference between the contributions of different polarization streams to the nonlinear phase shift and is denoted as enhanced CNN (ECNN). The numerical simulation results confirm the effectiveness of the method for a 64 Gbaud/s quadrature phase-shift keying (QPSK) polarization-division-multiplexed (PDM) coherent optical communication system with a fiber length of 320 km. The effects of finite impulse response (FIR) filter length, power into the fiber, and polarization mode dispersion on the PPE accuracy are examined. Finally, the results of the proposed method are monitored in the presence of several simultaneous power attenuation anomalies in the fiber optic link. It is found that the accuracy of the PPE substantially improves after using the proposed method, achieving a relative gain of up to 71%. When the modulation format is changed from QPSK to 16-ary quadrature amplitude modulation (16-QAM), and the fiber length is increased from 360 km to 480 km, the proposed method is still effective. This work provides a feasible solution for implementing fiber-longitudinal PPE, enabling significantly improved estimation accuracy in practical applications.https://www.mdpi.com/2304-6732/12/3/271fiber optics communicationfiber-longitudinal power profile estimationconvolutional neural networksnonlinear phase shiftpower attenuation anomalies
spellingShingle Daobin Wang
Kun Wen
Tiantian Bai
Ruiyang Xia
Zanshan Zhao
Guanjun Gao
Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation
Photonics
fiber optics communication
fiber-longitudinal power profile estimation
convolutional neural networks
nonlinear phase shift
power attenuation anomalies
title Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation
title_full Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation
title_fullStr Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation
title_full_unstemmed Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation
title_short Convolutional Neural Network-Based Fiber Optic Channel Emulator and Its Application to Fiber-Longitudinal Power Profile Estimation
title_sort convolutional neural network based fiber optic channel emulator and its application to fiber longitudinal power profile estimation
topic fiber optics communication
fiber-longitudinal power profile estimation
convolutional neural networks
nonlinear phase shift
power attenuation anomalies
url https://www.mdpi.com/2304-6732/12/3/271
work_keys_str_mv AT daobinwang convolutionalneuralnetworkbasedfiberopticchannelemulatoranditsapplicationtofiberlongitudinalpowerprofileestimation
AT kunwen convolutionalneuralnetworkbasedfiberopticchannelemulatoranditsapplicationtofiberlongitudinalpowerprofileestimation
AT tiantianbai convolutionalneuralnetworkbasedfiberopticchannelemulatoranditsapplicationtofiberlongitudinalpowerprofileestimation
AT ruiyangxia convolutionalneuralnetworkbasedfiberopticchannelemulatoranditsapplicationtofiberlongitudinalpowerprofileestimation
AT zanshanzhao convolutionalneuralnetworkbasedfiberopticchannelemulatoranditsapplicationtofiberlongitudinalpowerprofileestimation
AT guanjungao convolutionalneuralnetworkbasedfiberopticchannelemulatoranditsapplicationtofiberlongitudinalpowerprofileestimation