A QoT Estimation Method using EGN-assisted Machine Learning for Network Planning Applications

TL;DR

This paper introduces a machine learning-based QoT estimation method utilizing EGN-assisted features, significantly improving accuracy and efficiency in network planning by reducing lightpaths and enhancing SNR.

Contribution

It presents a novel ML model leveraging EGN-assisted SCI for QoT estimation, outperforming traditional closed-form GN methods in accuracy and network resource optimization.

Findings

1. Achieved an average SNR gain of 1.1 dB in link optimization.

2. Reduced the number of required lightpaths by 40% in planning scenarios.

3. Demonstrated superior accuracy over closed-form GN methods.

Abstract

An ML model based on precomputed per-channel SCI is proposed. Due to its superior accuracy over closed-form GN, an average SNR gain of 1.1 dB in an end-to-end link optimization and a 40% reduction in required lightpaths to meet traffic requests in a network planning scenario are shown.