G-OSNR estimation on dynamic PS-QAM channels using hybrid neural networks
Aspects of the present disclosure describe systems, methods and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping.
1. An improved system for estimating a general optical signal to noise ratio (G-OSNR) of optical signals exhibiting probabilistic-shaped quadrature amplitude modulation (PS-QAM), said system CHARACTERIZED BY:
a two-stage, hybrid neural network including a convolutional neural network (CNN) classifier in a first stage, followed by a second stage including a plurality of artificial neural networks (ANN) that estimates the G-OSNR after the CNN classification.
2. The improved system of claim 1 FURTHER CHARACTERIZED BY:
the CNN comprises several layers including 2 convolutional, 1 pooling, 1 flatten, and 2 fully-connected layers and 6 outputs for different shaping factor categorizations.
3. The improved system of claim 2 FURTHER CHARACTERIZED BY:
the ANN includes a plurality of ANN regressions to estimate the G-OSNR for various probabilistic-shaped channels.
4. The improved system of claim 3 FURTHER CHARACTERIZED BY:
the ANN includes two hidden layers each having 50 and 20 neurons, respectively.
5. The improved system of claim 3 FURTHER CHARACTERIZED BY:
a plurality of ANN training models, at least one for each differently classified group.