Estimating Quality of Transmission in a Live Production Network using Machine Learning

12/07/2021

∙

We demonstrate QoT estimation in a live network utilizing neural networks trained on synthetic data spanning a large parameter space. The ML-model predicts the measured lightpath performance with <0.5dB SNR error over a wide configuration range.

READ FULL TEXT

Estimating Quality of Transmission in a Live Production Network using Machine Learning

Copula-based synthetic data generation for machine learning emulators in weather and climate: application to a simple radiation model

Bayesian surrogate learning in dynamic simulator-based regression problems

SpoofGAN: Synthetic Fingerprint Spoof Images

Reducing Parameter Space for Neural Network Training

Experimental Demonstration of ML-Based DWDM System Margin Estimation

High-Fidelity State-of-Charge Estimation of Li-Ion Batteries Using Machine Learning

Feedback Detection for Live Predictors

Estimating Quality of Transmission in a Live Production Network using Machine Learning

Related Research

Copula-based synthetic data generation for machine learning emulators in weather and climate: application to a simple radiation model

Bayesian surrogate learning in dynamic simulator-based regression problems

SpoofGAN: Synthetic Fingerprint Spoof Images

Reducing Parameter Space for Neural Network Training

Experimental Demonstration of ML-Based DWDM System Margin Estimation

High-Fidelity State-of-Charge Estimation of Li-Ion Batteries Using Machine Learning

Feedback Detection for Live Predictors