ML-based Anomaly Detection in Optical Fiber Monitoring

2022/02/23 by Abdelli, Khouloud, Cho, Joo Yeon, Tropschug, Carsten
#Cryptography and Security (cs.CR) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2202.11756

Abstract

Secure and reliable data communication in optical networks is critical for high-speed internet. We propose a data driven approach for the anomaly detection and faults identification in optical networks to diagnose physical attacks such as fiber breaks and optical tapping. The proposed methods include an autoencoder-based anomaly detection and an attention-based bidirectional gated recurrent unit algorithm for the fiber fault identification and localization. We verify the efficiency of our methods by experiments under various attack scenarios using real operational data.

Related

• DeepALM: Holistic Optical Network Monitoring based on Machine Learning
• An Overview on Application of Machine Learning Techniques in Optical Networks
• Convolutional Neural Networks for Reflective Event Detection and Characterization in Fiber Optical Links Given Noisy OTDR Signals
• AI-Augmented OTDR Fault Localization Framework for Resilient Rural Fiber Networks in the United States
• Fault Monitoring in Passive Optical Networks using Machine Learning Techniques