Gated Recurrent Unit based Autoencoder for Optical Link Fault Diagnosis in Passive Optical Networks

TL;DR

This paper introduces a deep learning autoencoder model for accurate fault detection and localization in passive optical networks, demonstrating high accuracy and outperforming traditional methods.

Contribution

The paper presents a novel autoencoder-based deep learning approach specifically designed for fiber fault diagnosis in optical networks.

Findings

Fault detection accuracy of 97%

Localization RMSE of 0.18 meters

Outperforms conventional techniques

Abstract

We propose a deep learning approach based on an autoencoder for identifying and localizing fiber faults in passive optical networks. The experimental results show that the proposed method detects faults with 97% accuracy, pinpoints them with an RMSE of 0.18 m and outperforms conventional techniques.