☆ 4.6 Review

A review of machine learning-based failure management in optical networks

SCIENCE CHINA-INFORMATION SCIENCES (2022)

Related references

Note: Only part of the references are listed.

Article Computer Science, Hardware & Architecture

Domain adaptation and transfer learning for failure detection and failure-cause identification in optical networks across different lightpaths

Francesco Musumeci et al.

Summary: Optical network failure management (ONFM) is a promising application of machine learning (ML) in optical networking. However, the availability of data in operational networks often limits the deployment of ML-based ONFM solutions. Transfer learning (TL) and domain adaptation are possible solutions to this problem. Through experimental research, we find that domain adaptation can improve the accuracy of failure detection, and combining domain adaptation with model re-training can improve the accuracy of failure-cause identification.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

Potential failure cause identification for optical networks using deep learning with an attention mechanism

Chunyu Zhang et al.

Summary: This paper proposes a scheme for identifying potential failure causes in optical transport network boards using an attention mechanism. The experimental results show that the proposed scheme has high accuracy and can effectively identify potential failure causes, while improving the performance of the failure prediction model.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Experimental study of machine-learning-based detection and location of eavesdropping in end-to-end optical fiber communications

Haokun Song et al.

Summary: This study proposes a Machine Learning-based scheme to detect and locate physical-layer eavesdropping in optical fiber communications, achieving high accuracy through the use of Optical Performance Monitoring data and eye-diagrams as input. Experiments conducted in a fiber transmission system show promising results with ML classifiers achieving 100% and 92.76% accuracy in eavesdropping detection and location, respectively.

OPTICAL FIBER TECHNOLOGY (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Digital Longitudinal Monitoring of Optical Fiber Communication Link

Takeo Sasai et al.

Summary: This paper presents a method for reconstructing optical transmission channels by extracting physical characteristics of various link components from receiver-side digital signal processing. The method allows for the localization of anomaly components without direct measurements.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2022)

Add to Collection

Article Optics

Physics-Informed Neural Network for Nonlinear Dynamics in Fiber Optics

Xiaotian Jiang et al.

Summary: This study investigates a physics-informed neural network (PINN) that combines deep learning with physics to solve the nonlinear Schrodinger equation in fiber optics. PINN is systematically investigated and verified for multiple physical effects in optical fibers, and it exhibits better performance than data-driven neural networks while using less data. The results show that PINN is not only an effective partial differential equation solver, but also a prospective technique for scientific computing and automatic modeling in fiber optics.

LASER & PHOTONICS REVIEWS (2022)

Add to Collection

Article Computer Science, Hardware & Architecture

Optical network security management: requirements, architecture, and efficient machine learning models for detection of evolving threats [Invited]

Marija Furdek et al.

Summary: This paper proposes a novel functional block called the security operation center for automated security management in optical networks. Additionally, the study combines various learning techniques and dimensionality reduction methods to enhance the efficiency of processing high-dimensional optical performance monitoring data.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Performance comparisons between machine learning and analytical models for quality of transmission estimation in wavelength-division-multiplexed systems [Invited]

Jianing Lu et al.

Summary: By comparing quality-of-transmission estimation using machine learning and analytical models, it is found that in experimental settings with insufficient knowledge of system parameters, machine learning models generally estimate transmission quality more accurately than analytical models.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Optics

Predicting lifetime of optical components with Bayesian inference

Linas Smalakys et al.

Summary: This paper presents a framework for analyzing the extrapolation of optical component lifetime in high power or intensity optical systems using well-established methods of Bayesian statistics. The results show that the Bayesian lifetime analysis method is more accurate and reliable than the technique described in the ISO standard for analyzing LIDT fatigue data.

OPTICS EXPRESS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

ROADM-Induced Anomaly Localization and Evaluation for Optical Links Based on Receiver DSP and ML

Huazhi Lun et al.

Summary: With the advancement of elastic optical networks, optical communication systems are becoming more flexible and dynamic, but soft failures may lead to degradation in transmission quality and even service disruption. Using artificial neural networks and Gaussian process regression, soft failure locations can be accurately identified and anomaly values estimated.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Monitoring and diagnostic technologies using deep neural networks for predictive optical network maintenance [Invited]

Takafumi Tanaka et al.

Summary: In recent years, optical networks have become more complex, requiring autonomous optical network diagnosis and the support of machine learning. Another trend is to reduce capital expenditure/operational expenditure of optical transport equipment through whitebox hardware, open source software, and open interfaces. The paper describes in detail the concept of workflows for the whitebox transponder and demonstrates successful fiber bending detection as a use case.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Spectral processing techniques for efficient monitoring in optical networks

Fabiano Locatelli et al.

Summary: This study explores the placement of optical monitors in optical networks in different scenarios, proposing solutions and verifying them through simulation and experimental setups. Results show that the placement at the ingress scenario is more beneficial for parameter estimation accuracy.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Reflective fiber fault detection and characterization using long short-term memory

Khouloud Abdelli et al.

Summary: This paper proposes a novel multitask learning model based on long short-term memory to detect, locate, and estimate the reflectance of fiber reflective faults using telemetry data and optical time-domain reflectometry principle. Experimental results show that the method achieves good detection capability and high localization accuracy within a short time.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Reliable and scalable Kafka-based framework for optical network telemetry

Andrea Sgambelluri et al.

Summary: The paper proposes a Kafka-based monitoring framework that leverages telemetry service to accelerate failure detection and minimize response time. The framework demonstrates high scalability, low CPU load, low latency, and the ability to overcome core component failure without message loss in experimental validation.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Fault Localization based on Knowledge Graph in Software-Defined Optical Networks

Zhuotong Li et al.

Summary: In the era of the fifth-generation fixed network, optical networks need to support large bandwidth, low latency, high reliability, and intelligent management. Studies show that software-defined optical networks and artificial intelligence can enhance the performance and management capabilities of optical networks. By utilizing knowledge graphs and a reasoning model based on graph neural networks, analyzing network abnormalities and locating faults can be improved.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Optical Performance Monitoring of Multiple Parameters in Future Optical Networks

Dawei Wang et al.

Summary: Optical performance monitoring (OPM) is essential for managing future optical fiber communication networks, providing feedback on physical layer states to enable better network planning and diagnosis. By utilizing low-bandwidth coherent receivers and local lasers, a multiparameter OPM at intermediate nodes can scan optical spectrum, measure power, wavelength, OSNR, and other parameters for improved network performance.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Machine-learning-based soft-failure localization with partial software-defined networking telemetry

Kayol S. Mayer et al.

Summary: This paper evaluates an ML-based soft-failure localization framework in scenarios of partial telemetry. The framework is based on an artificial neural network trained by optical signal and noise power models, exhibiting excellent performance in scenarios of partial telemetry, practically interpolating the missing data and locating the faults accurately.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2021)

Add to Collection

Article Optics

Cause-aware failure detection using an interpretable XGBoost for optical networks

Chunyu Zhang et al.

Summary: This paper proposes a cause-aware failure detection scheme for optical transport network boards, using the XGBoost algorithm and determining important features related to failures through SHAP values. Experimental results show that the proposed scheme has excellent performance in detecting failures for two types of OTN boards.

OPTICS EXPRESS (2021)

Add to Collection

Article Computer Science, Information Systems

Soft-Failure Detection, Localization, Identification, and Severity Prediction by Estimating QoT Model Input Parameters

Sima Barzegar et al.

Summary: This study proposes a method of comparing QoT in optical devices to predict device failures by estimating the differences between estimated and measured values, achieving accurate detection and localization, and effectively identifying issues before degradation occurs.

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT (2021)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Transformer-based Alarm Context-Vectorization Representation for Reliable Alarm Root Cause Identification in Optical Networks

Jinwei Jia et al.

Summary: A Transformer-based technique is proposed for alarm root cause identification and correlation analysis, achieving an accuracy of 94.47% for three common root alarms and quantified correlation degrees for other correlated alarms.

2021 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATION (ECOC) (2021)

Add to Collection

Review Telecommunications

Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

Danshi Wang et al.

Summary: This paper explores the application of deep learning in optical communication, focusing on the contributions of different DL algorithms, including image recognition, sequential data analysis, data-driven channel modeling, and data augmentation with generative adversarial networks, among others.

FRONTIERS IN COMMUNICATIONS AND NETWORKS (2021)

Add to Collection

Article Computer Science, Hardware & Architecture

Coordination between control layer AI and on-board AI in optical transport networks [Invited]

Yongli Zhao et al.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Demonstration of a Novel Framework for Proactive Maintenance Using Failure Prediction and Bit Lossless Protection With Autonomous Network Diagnosis System

Fumikazu Inuzuka et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Dual-Stage Soft Failure Detection and Identification for Low-Margin Elastic Optical Network by Exploiting Digital Spectrum Information

Liang Shu et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2020)

Add to Collection

Review Computer Science, Hardware & Architecture

Machine learning for intelligent optical networks: A comprehensive survey

Rentao Gu et al.

JOURNAL OF NETWORK AND COMPUTER APPLICATIONS (2020)

Add to Collection

Article Optics

Low-complexity storage-reduced digital spectrum-based soft-failure management with Welch's method

Liang Shu et al.

OPTICS EXPRESS (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

Temporal data-driven failure prognostics using BiGRU for optical networks

Chunyu Zhang et al.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2020)

Add to Collection

Article Multidisciplinary Sciences

Advancing theoretical understanding and practical performance of signal processing for nonlinear optical communications through machine learning

Qirui Fan et al.

NATURE COMMUNICATIONS (2020)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Transfer Learning across Different Lightpaths for Failure-Cause Identification in Optical Networks

Francesco Musumeci et al.

2020 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATIONS (ECOC) (2020)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Digital Backpropagation for Optical Path Monitoring: Loss Profile and Passband Narrowing Estimation

Takeo Sasai et al.

2020 EUROPEAN CONFERENCE ON OPTICAL COMMUNICATIONS (ECOC) (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Soft Failure Identification for Long-haul Optical Communication Systems Based on One-dimensional Convolutional Neural Network

Huazhi Lun et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Learning From the Optical Spectrum: Failure Detection and Identification

Behnam Shariati et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Engineering, Electrical & Electronic

An Optical Communication's Perspective on Machine Learning and Its Applications

Faisal Nadeem Khan et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Engineering, Electrical & Electronic

Self-Taught Anomaly Detection With Hybrid Unsupervised/Supervised Machine Learning in Optical Networks

Xiaoliang Chen et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Optics

Dirty-data-based alarm prediction in self-optimizing large-scale optical networks

Boyuan Yan et al.

OPTICS EXPRESS (2019)

Add to Collection

Article Engineering, Electrical & Electronic

A Tutorial on Machine Learning for Failure Management in Optical Networks

Francesco Musumeci et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Engineering, Electrical & Electronic

A Dynamic Time Sequence Recognition and Knowledge Mining Method Based on the Hidden Markov Models (HMMs) for Pipeline Safety Monitoring With Φ-OTDR

Huijuan Wu et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2019)

Add to Collection

Article Chemistry, Analytical

An Event Recognition Method for Φ-OTDR Sensing System Based on Deep Learning

Yi Shi et al.

SENSORS (2019)

Add to Collection

Article Computer Science, Information Systems

Machine Learning-Based Multifunctional Optical Spectrum Analysis Technique

Danshi Wang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

An Overview on Application of Machine Learning Techniques in Optical Networks

Francesco Musumeci et al.

IEEE COMMUNICATIONS SURVEYS AND TUTORIALS (2019)

Add to Collection

Article Computer Science, Information Systems

Dealing With Alarms in Optical Networks Using an Intelligent System

Danshi Wang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Hardware & Architecture

Soft Failure Localization During Commissioning Testing and Lightpath Operation

A. P. Vela et al.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Cognitive Assurance Architecture for Optical Network Fault Management

Danish Rafique et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2018)

Add to Collection

Article Computer Science, Hardware & Architecture

Leveraging Statistical Machine Learning to Address Failure Localization in Optical Networks

T. Panayiotou et al.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2018)

Add to Collection

Article Computer Science, Hardware & Architecture

Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]

Danish Rafique et al.

JOURNAL OF OPTICAL COMMUNICATIONS AND NETWORKING (2018)

Add to Collection

Article Optics

SOON: self-optimizing optical networks with machine learning

Yongli Zhao et al.

OPTICS EXPRESS (2018)

Add to Collection

Article Engineering, Electrical & Electronic

Modulation Format Recognition and OSNR Estimation Using CNN-Based Deep Learning

Danshi Wang et al.

IEEE PHOTONICS TECHNOLOGY LETTERS (2017)

Add to Collection

Article Engineering, Electrical & Electronic

BER Degradation Detection and Failure Identification in Elastic Optical Networks

Alba P. Vela et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2017)

Add to Collection

Article Optics

Failure prediction using machine learning and time series in optical network

Zhilong Wang et al.

OPTICS EXPRESS (2017)

Add to Collection

Article Optics

Intelligent constellation diagram analyzer using convolutional neural network-based deep learning

Danshi Wang et al.

OPTICS EXPRESS (2017)

Add to Collection

Article Engineering, Electrical & Electronic

Optical Performance Monitoring: A Review of Current and Future Technologies

Zhenhua Dong et al.

JOURNAL OF LIGHTWAVE TECHNOLOGY (2016)

Add to Collection

Article Computer Science, Information Systems

Active monitoring and alarm management for fault localization in transparent all-optical networks

Sava Stanic et al.

IEEE Transactions on Network and Service Management (2010)

Add to Collection

© Peeref 2019-2024. All rights reserved.