Fiber Fault
Fiber fault detection and localization in optical networks is a critical area of research aiming to improve network reliability and security. Current efforts focus on leveraging machine learning, particularly deep learning architectures like convolutional neural networks (CNNs), recurrent neural networks (RNNs, including LSTMs and GRUs), and autoencoders, to analyze optical time-domain reflectometry (OTDR) data and other optical signals for rapid and accurate fault identification. These advanced techniques offer significant improvements over traditional methods, enhancing the speed and accuracy of fault detection and localization, ultimately leading to more robust and efficient optical communication systems.
Papers
Gated Recurrent Unit based Autoencoder for Optical Link Fault Diagnosis in Passive Optical Networks
Khouloud Abdelli, Florian Azendorf, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
Convolutional Neural Networks for Reflective Event Detection and Characterization in Fiber Optical Links Given Noisy OTDR Signals
Khouloud Abdelli, Helmut Griesser, Stephan Pachnicke
Machine Learning-based Anomaly Detection in Optical Fiber Monitoring
Khouloud Abdelli, Joo Yeon Cho, Florian Azendorf, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke
Reflective Fiber Faults Detection and Characterization Using Long-Short-Term Memory
Khouloud Abdelli, Helmut Griesser, Peter Ehrle, Carsten Tropschug, Stephan Pachnicke
Optical Fiber Fault Detection and Localization in a Noisy OTDR Trace Based on Denoising Convolutional Autoencoder and Bidirectional Long Short-Term Memory
Khouloud Abdelli, Helmut Griesser, Carsten Tropschug, Stephan Pachnicke