Conference paper
Machine learning-based EDFA Gain Model Generalizable to Multiple Physical Devices
Department of Photonics Engineering, Technical University of Denmark1
Machine Learning in Photonic Systems, Department of Photonics Engineering, Technical University of Denmark2
Ultra-fast Optical Communication, Department of Photonics Engineering, Technical University of Denmark3
Coding and Visual Communication, Department of Photonics Engineering, Technical University of Denmark4
Centre of Excellence for Silicon Photonics for Optical Communications, Centers, Technical University of Denmark5
We report a neural-network based erbium-doped fiber amplifier (EDFA) gain model built from experimental measurements. The model shows low gain-prediction error for both the same device used for training (MSE leq 0.04 dB^2) and different physical units of the same make (generalization MSEleq 0.06 dB^2).
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2020 |
Pages: | 1-4 |
Proceedings: | 46<sup>th</sup> European Conference on Optical Communication |
ISBN: | 1728173612 , 1728173620 , 9781728173610 and 9781728173627 |
Types: | Conference paper |
DOI: | 10.1109/ECOC48923.2020.9333297 |
ORCIDs: | Da Ros, Francesco , De Moura, Uiara Celine and Yankov, Metodi P. |