Skip to content

MoeinDSP/Optical-Failure-Localization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Optical-Failure-Localization

This project aims to localize soft failures in an optical network comprising four nodes connected in series, creating three links (Figure 1.1). Each node has a monitor at its input port that provides OSNR (Optical Signal-to-Noise Ratio) samples. A fault can happen at any of the three links, and our objective is to determine the faulty link. Hence, we use the OSNR values to determine key features, and train machine-learning algorithms to localize the fault. Moreover, to be aware of the correctness of ML-based decisions, we used Explainable AI (XAI). XAI techniques allow uncovering the reasoning behind the ML model to a human expert, making ML models more trustable and, hence, more likely to be adopted practically.

This repository contains in-class activities for the "Network Measurement and Data Analysis" course taught by Prof. Redondi and Prof. Musumeci at Politecnico di Milano.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published