Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning
A novel technique is proposed for joint multi-impairment optical performance monitoring (OPM) with bit-rate and modulation format identification (BR-MFI) in next-generation heterogeneous optic communication networks by convolution neural network (CNN)-based deep multi-task learning (MTL) on asynchro...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Photonics Journal |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8463576/ |
id |
doaj-3f1de60f95024f1993cd23a4e897fbc1 |
---|---|
record_format |
Article |
spelling |
doaj-3f1de60f95024f1993cd23a4e897fbc12021-03-29T17:49:55ZengIEEEIEEE Photonics Journal1943-06552018-01-0110511210.1109/JPHOT.2018.28699728463576Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task LearningXiaojie Fan0https://orcid.org/0000-0001-9990-1885Yulai Xie1Fang Ren2https://orcid.org/0000-0002-2251-9220Yiying Zhang3Xiaoshan Huang4Wei Chen5Tianwen Zhangsun6Jianping Wang7https://orcid.org/0000-0002-8729-9185School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaHitachi (China) Research and Development Co., Ltd., Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaSchool of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, ChinaA novel technique is proposed for joint multi-impairment optical performance monitoring (OPM) with bit-rate and modulation format identification (BR-MFI) in next-generation heterogeneous optic communication networks by convolution neural network (CNN)-based deep multi-task learning (MTL) on asynchronous delay-tap sampling phase portraits. Instead of treating the monitoring and identification tasks as separate problems, a novel MTL technique is used to joint optimization of them utilizing the ability of feature extraction and feature sharing. Compared with principal component analysis-based pattern recognition algorithm, CNN-based MTL achieves the better accuracies and has a shorter processing time (~56 ms). The combination signals of three modulation formats and two bit rates under various impairments are used in numerical simulation. For OPM, the results show monitoring of optical signal-to-noise ratio, chromatic dispersion, and differential group delay with root-mean-square error of 0.73 dB, 1.34 ps/nm, and 0.47 ps, respectively. Similarly, for BR-MFI, even in the case of limited training data, 100% accuracies can be achieved. Additionally, the effects of training data size, task weights, and model structure on CNN-based MTL performance are comprehensively studied. The proposed technique can intelligently analyze the signals of future heterogeneous optic communication networks, and the analysis results are helpful for better management of optical networks.https://ieeexplore.ieee.org/document/8463576/Optical performance monitoring (OPM)bit-rate and modulation format identification (BR-MFI)convolution neural network (CNN)deep multi-task learning (MTL)asynchronous delay-tap sampling (ADTS) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaojie Fan Yulai Xie Fang Ren Yiying Zhang Xiaoshan Huang Wei Chen Tianwen Zhangsun Jianping Wang |
spellingShingle |
Xiaojie Fan Yulai Xie Fang Ren Yiying Zhang Xiaoshan Huang Wei Chen Tianwen Zhangsun Jianping Wang Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning IEEE Photonics Journal Optical performance monitoring (OPM) bit-rate and modulation format identification (BR-MFI) convolution neural network (CNN) deep multi-task learning (MTL) asynchronous delay-tap sampling (ADTS) |
author_facet |
Xiaojie Fan Yulai Xie Fang Ren Yiying Zhang Xiaoshan Huang Wei Chen Tianwen Zhangsun Jianping Wang |
author_sort |
Xiaojie Fan |
title |
Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning |
title_short |
Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning |
title_full |
Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning |
title_fullStr |
Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning |
title_full_unstemmed |
Joint Optical Performance Monitoring and Modulation Format/Bit-Rate Identification by CNN-Based Multi-Task Learning |
title_sort |
joint optical performance monitoring and modulation format/bit-rate identification by cnn-based multi-task learning |
publisher |
IEEE |
series |
IEEE Photonics Journal |
issn |
1943-0655 |
publishDate |
2018-01-01 |
description |
A novel technique is proposed for joint multi-impairment optical performance monitoring (OPM) with bit-rate and modulation format identification (BR-MFI) in next-generation heterogeneous optic communication networks by convolution neural network (CNN)-based deep multi-task learning (MTL) on asynchronous delay-tap sampling phase portraits. Instead of treating the monitoring and identification tasks as separate problems, a novel MTL technique is used to joint optimization of them utilizing the ability of feature extraction and feature sharing. Compared with principal component analysis-based pattern recognition algorithm, CNN-based MTL achieves the better accuracies and has a shorter processing time (~56 ms). The combination signals of three modulation formats and two bit rates under various impairments are used in numerical simulation. For OPM, the results show monitoring of optical signal-to-noise ratio, chromatic dispersion, and differential group delay with root-mean-square error of 0.73 dB, 1.34 ps/nm, and 0.47 ps, respectively. Similarly, for BR-MFI, even in the case of limited training data, 100% accuracies can be achieved. Additionally, the effects of training data size, task weights, and model structure on CNN-based MTL performance are comprehensively studied. The proposed technique can intelligently analyze the signals of future heterogeneous optic communication networks, and the analysis results are helpful for better management of optical networks. |
topic |
Optical performance monitoring (OPM) bit-rate and modulation format identification (BR-MFI) convolution neural network (CNN) deep multi-task learning (MTL) asynchronous delay-tap sampling (ADTS) |
url |
https://ieeexplore.ieee.org/document/8463576/ |
work_keys_str_mv |
AT xiaojiefan jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT yulaixie jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT fangren jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT yiyingzhang jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT xiaoshanhuang jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT weichen jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT tianwenzhangsun jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning AT jianpingwang jointopticalperformancemonitoringandmodulationformatx002fbitrateidentificationbycnnbasedmultitasklearning |
_version_ |
1724197152339525632 |