SPJun 13, 2022
Flexible Raman Amplifier Optimization Based on Machine Learning-aided Physical Stimulated Raman Scattering ModelMetodi Plamenov Yankov, Francesco Da Ros, Uiara Celine de Moura et al.
The problem of Raman amplifier optimization is studied. A differentiable interpolation function is obtained for the Raman gain coefficient using machine learning (ML), which allows for the gradient descent optimization of forward-propagating Raman pumps. Both the frequency and power of an arbitrary number of pumps in a forward pumping configuration are then optimized for an arbitrary data channel load and span length. The forward propagation model is combined with an experimentally-trained ML model of a backward-pumping Raman amplifier to jointly optimize the frequency and power of the forward amplifier's pumps and the powers of the backward amplifier's pumps. The joint forward and backward amplifier optimization is demonstrated for an unrepeatered transmission of 250 km. A gain flatness of $<$ 1~dB over 4 THz is achieved. The optimized amplifiers are validated using a numerical simulator.
LGNov 23, 2021
Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICsAli Cem, Siqi Yan, Uiara Celine de Moura et al.
We experimentally compare simple physics-based vs. data-driven neural-network-based models for offline training of programmable photonic chips using Mach-Zehnder interferometer meshes. The neural-network model outperforms physics-based models for a chip with thermal crosstalk, yielding increased testing accuracy.
SPSep 11, 2020
Power Evolution Prediction and Optimization in a Multi-span System Based on Component-wise System ModelingMetodi P. Yankov, Uiara Celine de Moura, Francesco Da Ros
Cascades of a machine learning-based EDFA gain model trained on a single physical device and a fully differentiable stimulated Raman scattering fiber model are used to predict and optimize the power profile at the output of an experimental multi-span fully-loaded C-band optical communication system.
SPSep 11, 2020
Machine learning-based EDFA Gain Model Generalizable to Multiple Physical DevicesFrancesco Da Ros, Uiara Celine de Moura, Metodi P. Yankov
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 MSE $\leq$ 0.06 dB$^2$).