arXiv subjects
Publications and source records attributed to Matteo Lonardi.
We propose a novel unsupervised anomaly detection approach using generative adversarial networks and SOP-derived spectrograms. Demonstrating remarkable efficacy, our method achieves over 97% accuracy on SOP datasets from both submarine and terrestrial fiber links, all achieved without the need for labelled data.
We introduce a novel weather-adaptive approach for multi-step forecasting of multi-scale SOP changes in aerial fiber links. By harnessing the discrete wavelet transform and incorporating weather data, our approach improves forecasting accuracy by over 65% in RMSE and 63% in MAPE compared to baselines.
We present a method to measure the spectral density of in-band optical transmission impairments without coherent electrical reception and digital signal processing at the receiver. We determine the method's accuracy by numerical simulations and show experimentally its feasibility, including the measure of in-band nonlinear distortions power densities.
We present a theoretical model that fully supports the recently disclosed generalized droop formula (GDF) for calculating the signal-to-noise ratio (SNR) of constant-output power (COP) amplified dispersion-uncompensated coherent links operated at very low SNR. We compare the GDF to the better known Gaussian noise (GN) model. A key finding is that the end-to-end model underlying the GDF is a concatenation of per-span first-order regular perturbation (RP1) models with end-span power renormalization. This fact allows the GDF to well reproduce the SNR of highly nonlinear systems, well beyond the RP1 limit underlying the GN model. The GDF is successfully extended to the case where the bandwidth/modes of the COP amplifiers are not entirely filled by the transmitted multiplex. Finally, the GDF is extended to constant-gain (CG) amplifier chains and is shown to improve on known GN models of highly nonlinear propagation with CG amplifiers.