Add to BibSonomyAbstract
We implement a cascaded learning framework using component-level EDFA models for optical power spectrum prediction in multi-span networks, achieving a mean absolute error of 0.17 dB across 6 spans and 12 EDFAs with only one-shot measurement.
© 2024 The Author(s)
PDF ArticleMore Like This
Optical Signal Spectrum Prediction Using Machine Learning and In-line Channel Monitors in a Multi-span ROADM System
Zehao Wang, Emmanuel Akinrintoyo, Dan Kilper, and Tingjun Chen
We3B.5 European Conference and Exhibition on Optical Communication (ECOC) 2022
Transfer Learning-based ROADM EDFA Wavelength Dependent Gain Prediction Using Minimized Data Collection
Zehao Wang, Dan Kilper, and Tingjun Chen
Th2A.1 Optical Fiber Communication Conference (OFC) 2023
Recalibration Learning: Enabling Universal Transfer of ML Model of Gain and NF for Remote Optically Pumped Amplifiers
Arthur Minakhmetov, Benjamin Prieur, Maël Le Monnier, Delphine Rouvillain, and Bruno Lavigne
M3I.2 Optical Fiber Communication Conference (OFC) 2024