Confidential Detection of Multiple Failures in Optical Networks: an Experimental Evaluation
Mathaus Ferreira Da Silva, Andrea Sgambelluri, Alessandro Pacini, Francesco Paolucci, A. Green, David Mascareñas, Luca Valcarenghi · 2023
This paper presents a Machine Learning technique based on Principal Component Analysis (PCA) combined with telemetry data scrambling to detect multiple types of failure in optical networks while preserving data confidentiality. Experiments in an optical testbed show the effectiveness of the proposed solution.