Machine Learning Model for EDFA Predicting SHB Effects

Publication Date: 9/22/2024

Event: 2024 European Conference on Optical Communication (ECOC)

Reference: pp. 1-4, 2024

Authors: Fatih Yaman, NEC Laboratories America, Inc.; Andrea D’Amico, NEC Laboratories America, Inc.; Eduardo Mateo, NEC Corporation; Takanori Inoue, NEC Corporation; Yoshihisa Inada, NEC Corporation

Abstract: Experiments show that the machine learning model of an EDFA is capable of modelling spectral hole burning effects accurately. As a result, it significantly outperforms black-box models that neglect inhomogeneous effects. The model achieves a record average RMSE of 0.0165 dB between the model predictions and measurements.

Publication Link: