SOP-Based Anomaly Detection Leveraging Machine Learning for Proactive Optical Restoration

This paper presents an experimental proof-ofconcept for detecting malicious mechanical vibrations in opticalnetworks using Machine Learning (ML) techniques. The studyleverages the State of Polarization (SOP) as a real-time sensingmechanism for the identification of anomalous disturbances, likethose caused by drilling, which can lead to fiber cuts and significant network disruptions. The proposed ML-based approachis able to continuously monitor SOP fluctuations, enabling theearly detection of vibrations and proactive mitigation of potential network failures. By leveraging advanced ML algorithms,the model effectively identifies between normal environmentalvibrations and critical, harmful disturbances. This capabilityensures timely intervention to protect the network infrastructure.The ML model achieved a vibration detection accuracy of 95%,which demonstrates it’s high reliability in distinguishing benignanomalies from disruptive anomalies. This level of precisionsignificantly enhances the stability, resilience, and operationalefficiency of the optical network. This leads to a reduction inthe likelihood of service outages and physical infrastructuredamage. The results show the potential of combining real-timeSOP monitoring with ML-based analytics to advance networkmanagement strategies