Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios

Nonlinear noise power (NLNP) estimation, optical signal-to-noise ratio (OSNR) monitoring, and modulation format identification (MFI) are crucial for optical performance monitoring (OPM) in future dynamic WDM optical networks. This paper proposes an OPM scheme to simultaneously implement these three...

Full description

Saved in:
Bibliographic Details
Main Authors: Di Zhang, Junyao Shi, Yameng Cao, Yan Ling Xue
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Photonics
Subjects:
Online Access:https://www.mdpi.com/2304-6732/12/4/324
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850180708876681216
author Di Zhang
Junyao Shi
Yameng Cao
Yan Ling Xue
author_facet Di Zhang
Junyao Shi
Yameng Cao
Yan Ling Xue
author_sort Di Zhang
collection DOAJ
description Nonlinear noise power (NLNP) estimation, optical signal-to-noise ratio (OSNR) monitoring, and modulation format identification (MFI) are crucial for optical performance monitoring (OPM) in future dynamic WDM optical networks. This paper proposes an OPM scheme to simultaneously implement these three tasks in both single-channel and WDM systems by combining amplitude-differential phase histograms (ADPH) with the MAML-CNN-ATT algorithm that integrates model-agnostic meta-learning (MAML), the convolutional neural network (CNN), and the attention mechanism (ATT). The meta-learning algorithms can learn optimal initial model parameters across multiple related tasks, enabling them to quickly adapt to new tasks through fine-tuning with a small amount of data. This results in superior self-adaptability and generalizability, making them more suitable for WDM scenarios than the transfer learning (TL) algorithms. The CNN-ATT algorithm can effectively extract comprehensive features, capturing both local and global dependencies, thus improving the quality of the feature representation. The ADPH sequence data combine the amplitude information and the differential phase information that indicate the signal’s overall characteristics. The results demonstrate that the MAML-CNN-ATT algorithm achieves errors of less than 1 dB in both NLNP estimation and OSNR monitoring tasks while achieving 100% accuracy in the MFI task. It exhibits excellent OPM performance not only in the single channel but also in the WDM transmission, with only a few steps of fine-tuning. The MAML-CNN-ATT algorithm provides a solution with high performance and rapid self-adaptation for the multi-task OPM in dynamic optical networks.
format Article
id doaj-art-2df4915566c245bca16f67e7e918bc9c
institution OA Journals
issn 2304-6732
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Photonics
spelling doaj-art-2df4915566c245bca16f67e7e918bc9c2025-08-20T02:18:04ZengMDPI AGPhotonics2304-67322025-03-0112432410.3390/photonics12040324Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission ScenariosDi Zhang0Junyao Shi1Yameng Cao2Yan Ling Xue3Shanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronics Engineering, East China Normal University, Shanghai 200241, ChinaShanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronics Engineering, East China Normal University, Shanghai 200241, ChinaShanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronics Engineering, East China Normal University, Shanghai 200241, ChinaShanghai Key Laboratory of Multidimensional Information Processing, School of Communication and Electronics Engineering, East China Normal University, Shanghai 200241, ChinaNonlinear noise power (NLNP) estimation, optical signal-to-noise ratio (OSNR) monitoring, and modulation format identification (MFI) are crucial for optical performance monitoring (OPM) in future dynamic WDM optical networks. This paper proposes an OPM scheme to simultaneously implement these three tasks in both single-channel and WDM systems by combining amplitude-differential phase histograms (ADPH) with the MAML-CNN-ATT algorithm that integrates model-agnostic meta-learning (MAML), the convolutional neural network (CNN), and the attention mechanism (ATT). The meta-learning algorithms can learn optimal initial model parameters across multiple related tasks, enabling them to quickly adapt to new tasks through fine-tuning with a small amount of data. This results in superior self-adaptability and generalizability, making them more suitable for WDM scenarios than the transfer learning (TL) algorithms. The CNN-ATT algorithm can effectively extract comprehensive features, capturing both local and global dependencies, thus improving the quality of the feature representation. The ADPH sequence data combine the amplitude information and the differential phase information that indicate the signal’s overall characteristics. The results demonstrate that the MAML-CNN-ATT algorithm achieves errors of less than 1 dB in both NLNP estimation and OSNR monitoring tasks while achieving 100% accuracy in the MFI task. It exhibits excellent OPM performance not only in the single channel but also in the WDM transmission, with only a few steps of fine-tuning. The MAML-CNN-ATT algorithm provides a solution with high performance and rapid self-adaptation for the multi-task OPM in dynamic optical networks.https://www.mdpi.com/2304-6732/12/4/324meta-learning algorithmconvolutional neural networkattention mechanismoptical performance monitoringamplitude-differential phase histogramWDM transmission
spellingShingle Di Zhang
Junyao Shi
Yameng Cao
Yan Ling Xue
Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios
Photonics
meta-learning algorithm
convolutional neural network
attention mechanism
optical performance monitoring
amplitude-differential phase histogram
WDM transmission
title Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios
title_full Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios
title_fullStr Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios
title_full_unstemmed Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios
title_short Joint Three-Task Optical Performance Monitoring with High Performance and Superior Generalizability Using a Meta-Learning-Based Convolutional Neural Network-Attention Algorithm and Amplitude-Differential Phase Histograms Across WDM Transmission Scenarios
title_sort joint three task optical performance monitoring with high performance and superior generalizability using a meta learning based convolutional neural network attention algorithm and amplitude differential phase histograms across wdm transmission scenarios
topic meta-learning algorithm
convolutional neural network
attention mechanism
optical performance monitoring
amplitude-differential phase histogram
WDM transmission
url https://www.mdpi.com/2304-6732/12/4/324
work_keys_str_mv AT dizhang jointthreetaskopticalperformancemonitoringwithhighperformanceandsuperiorgeneralizabilityusingametalearningbasedconvolutionalneuralnetworkattentionalgorithmandamplitudedifferentialphasehistogramsacrosswdmtransmissionscenarios
AT junyaoshi jointthreetaskopticalperformancemonitoringwithhighperformanceandsuperiorgeneralizabilityusingametalearningbasedconvolutionalneuralnetworkattentionalgorithmandamplitudedifferentialphasehistogramsacrosswdmtransmissionscenarios
AT yamengcao jointthreetaskopticalperformancemonitoringwithhighperformanceandsuperiorgeneralizabilityusingametalearningbasedconvolutionalneuralnetworkattentionalgorithmandamplitudedifferentialphasehistogramsacrosswdmtransmissionscenarios
AT yanlingxue jointthreetaskopticalperformancemonitoringwithhighperformanceandsuperiorgeneralizabilityusingametalearningbasedconvolutionalneuralnetworkattentionalgorithmandamplitudedifferentialphasehistogramsacrosswdmtransmissionscenarios