Journal of Lightwave Technology · 2021 · 92 citations · 41 references
Optical transmission links are generally composed of optical fibers, optical amplifiers, and optical filters. In this paper, we present a channel reconstruction method (CRM) that extracts physical characteristics of multiple link components such as longitudinal fiber losses, chromatic dispersion (CD), multiple amplifiers’ gain spectra, and multiple filters’ responses, only from receiver-side (Rx) digital signal processing (DSP) of data-carrying signals. The concept is to reconstruct a virtual copy of an actual transmission channel in the digital domain, where optical fibers and amplifiers are modeled as the split-step Fourier method for the Manakov equation while optical filters are emulated as complex-valued finite impulse response filters. We estimate the model parameters such as losses, CD, gains, and filter responses from boundary conditions, i.e., transmitted and received signals. Experimental results show that, unlike traditional analog testing devices such as optical time-domain reflectometers and optical spectrum analyzers, CRM visualizes multi-span characteristics of fibers, amplifiers, and filters in Rx DSP, and thus localizes anomaly components among multiple ones without direct measurement.
41
Theory of the backpropagation neural network
Hecht-Nielsen · 1989 · 2.2K citations
Engineering, Machine Learning, Neural Networks (Machine Learning) +20
EGN model of non-linear fiber propagation
Andrea Carena, Gabriella Bosco, Vittorio Curri et al. · Optics Express · 2014 · 462 citations · Full text