UPCommons. Portal del coneixement obert de la UPC
Publicación
Contribución de congreso (ConferenceOutput)
ML-based modeling of EDFA pluggable modules for OSNR estimation
Erbium doped fiber amplifiers (EDFA) return an output dependent on the target gain, the channel-loading configuration, as well as the input channels' wavelengths and powers. Due to absence of accurate analytical models, in this article we investigate machine learning methods and their use for estimating the output of an EDFA pluggable module. First, we characterize experimentally a preamplifier. Secondly, after time demanding hyperparameter optimizations we evaluate the performances of deep learning and ensemble methods. Then, we evaluate the generalizability of the models and the benefits of transfer learning strategies to reduce the generalization error. Finally, we propose an algorithm for OSNR estimation that we evaluate based on experimental data., The research leading to these results has received funding from the European Community through the MSCA MENTOR (G.A. 956713), the European Union's Horizon Europe research and innovation programmes SEASON (G.A. 101096120) and ALLEGRO (G.A. 101092766) and from the ICREA Institution. Moreover, this research has received partial support from the European Union’s project HORSE (G.A. 101096342) and by the NextGenerationEU projects PRIN 2022 (CUP E53D23000760006, identification code 2022MWBFEE001) and SOW (CUP E63C22000970007, identification code CN00000013)., Peer Reviewed