SNR margins between partially and fully loaded DWDM systems are estimated without detailed knowledge of the network. The ML model, trained on simulation data, achieves accurate predictions on experimental data with an RMSE of 0.16 dB.
Cite
@article{arxiv.2302.08275,
title = {Experimental Demonstration of ML-Based DWDM System Margin Estimation},
author = {Jasper Müller and Frank Slyne and Kaida Kaeval and Sebastian Troia and Tobias Fehenberger and Jörg-Peter Elbers and Daniel C. Kilper and Marco Ruffini and Carmen Mas-Machuca},
journal= {arXiv preprint arXiv:2302.08275},
year = {2023}
}
Comments
This work has been partially funded by the German Federal Ministry of Education and Research in the CELTIC-NEXT project AI-NET-PROTECT (#16KIS1279K) and in the programme of "Souver\"an. Digital. Vernetzt." joint project 6G-life (#16KISK002). Work was also funded by Science Foundation Ireland projects OpenIreland (18/RI/5721) and 13/RC/2077 p2