Matteo Lonardi

Matteo Lonardi

Auto-generated profile, based on publicly available information

Matteo Lonardi

Nokia, Vimercate, Italy

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 January 2020 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
ABAlberto Bononi
Alberto Bononi
JAJean-Christophe Antona
Jean-Christophe Antona
MLMatteo Lonardi
Matteo Lonardi
ACAlexis Carbo-Meseguer
Alexis Carbo-Meseguer
PSPaolo Serena
Paolo Serena
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 coherent links operated at very low SNR. For single-mode nonlinear COP links we compare the GDF-SNR to the better known generalized SNR (GSNR) that uses the Gaussian noise (GN) model for constant-gain (CG) amplifiers. We find that at all medium to large SNRs the GSNR well matches with the GDF, while at GSNR below 6dB the GSNR over-estimates the correct GDF-SNR by more than 0.5dB. Fortunately, the GDF-SNR turns out to be approximately a simple function of the GSNR, which allows adaptation of the widespread GSNR also to very low SNR links. A key finding of this paper 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 CG amplified links and is shown to improve on known GN models of highly nonlinear propagation with CG amplifiers.

24 September 2021 in IEEE Photonics Technology Letters
Verified
Journal Article
Closed access
AMA. May
A. May
FBF. Boitier
F. Boitier
EAElie Awwad
Elie Awwad
PRP. Ramantanis
P. Ramantanis
MLM. Lonardi
M. Lonardi
PCP. Ciblat
P. Ciblat
We propose a method to estimate the amplitude of an unexpected power loss which, leveraging on a calibration, enables the real-time monitoring of a network link. It is based on an existing fiber-longitudinal power profile evaluation technique. The reliability of the method is assessed experimentally. When the anomaly is located at 0 km from the beginning of the span, the estimation bias is smaller than 0.2 dB for losses up to 10 dB. When the anomaly is located at 25 km from the beginning of the span, the same estimation bias is observed but for losses up to 5 dB. In both cases, the standard deviation of the estimation is smaller than 0.2 dB.

10 April 2020 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
MLMatteo Lonardi
Matteo Lonardi
JPJelena Pesic
Jelena Pesic
PJPhilippe Jenneve
Philippe Jenneve
PRPetros Ramantanis
Petros Ramantanis
NRNicola Rossi
Nicola Rossi
SBSebastien Bigo
Sebastien Bigo
We present a linear-to-nonlinear power ratio monitor based on a shallow artificial neural network and the optical power spectrum. The neural network is trained with experimental pairs of input single-channel optical power spectra and output optimal power corrections, i.e., power amendments that lead to the power level maximizing the performance in terms of the signal-to-noise ratio. The technique is tested and shows the capability of providing up to 1 dB of signal-to-noise ratio gain in the ±3 dB region around the actual optimal power. Furthermore, the neural network does not recommend power variations resulting in a severe signal-to-noise ratio penalty (max -0.12 dB). Here, we extend our previously conference contribution by providing further insight into the theoretical background and some additional technical results in the direction of proving the connection between the optical power spectrum and the optimal power correction, i.e., the linear-to-nonlinear power ratio.

26 October 2021 in Journal of Optical Communications and Networking
Verified
Journal Article
Closed access
MLMatteo Lonardi
Matteo Lonardi
JPJelena Pesic
Jelena Pesic
TZThierry Zami
Thierry Zami
ESEmmanuel Seve
Emmanuel Seve
NRNicola Rossi
Nicola Rossi
In the present day, the evaluation of machine learning (ML) as a candidate for substituting analytical quality of transmission (QoT) estimators is done in a compartmentalized way. The assessment is not produced from a global optical network design perspective and with accurate optical design metrics; on the contrary, the evaluation heavily focuses on the physical layer impairment precision capabilities while underemphasizing the effects at the network layer. In this paper, we recommend a suitable methodology for evaluating the QoT substitution based on the foundational idea that different QoT estimators should be examined on a comparative basis by analyzing network-relevant metrics at parity of availability performance. Pragmatically, we recommend comparing performance estimation solutions through the aggregate network throughput, i.e., capacity, at the equity of their overestimation likelihood, which drives system margins. To demonstrate the need for such a network viewpoint and illustrate the potential drawbacks of an inadequate assessment of the QoT substitution, we use the proposed method in several scenarios (altering network topologies, input parameter uncertainty conditions, and availability requirements), showing that we can achieve gains in QoT estimation error or design margins while observing notable losses in terms of network throughput. Considering the results were contrary to what one may expect, we decided to undergo a statistical analysis in order to investigate and grasp the consequences of the model error distribution in relation to the network capacity.

17 December 2024 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
KAKhouloud Abdelli
Khouloud Abdelli
MLMatteo Lonardi
Matteo Lonardi
FBFabien Boitier
Fabien Boitier
DCDiego Correa
Diego Correa
JGJurgen Gripp
Jurgen Gripp
PLPatricia Layec
Patricia Layec
Monitoring the state of polarization (SOP) in optical communication networks is vital for maintaining network reliability and performance. SOP data, influenced by environmental factors, presents significant challenges for conventional methods due to its multidimensional nature and susceptibility to noise. Machine learning (ML) algorithms provide a promising solution by effectively learning complex patterns in SOP data, thereby enhancing anomaly detection capabilities. In this paper, we introduce an enhanced vision transformer-based approach for anomaly classification and localization in SOP data. Our method leverages spectrograms derived from continuous SOP measurements and has been validated using experimental data from a 2600 km bidirectional link. The proposed approach achieves an accuracy of 99% and a timestamping precision with a root mean square error (RMSE) of 7 ms. Comparative evaluations against several ML baselines underscore the superiority of our method, particularly in accurately localizing SOP transients within spectrograms and handling overlapping events, though these are treated as single combined events. These results reaffirm the efficacy of our approach in improving anomaly classification and localization capabilities in optical networks.

10 June 2022 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
JGJoana Girard-Jollet
Joana Girard-Jollet
MLMatteo Lonardi
Matteo Lonardi
PRPetros Ramantanis
Petros Ramantanis
PSPaolo Serena
Paolo Serena
CLChiara Lasagni
Chiara Lasagni
JAJean-Christophe Antona
Jean-Christophe Antona
In this paper, we propose a novel technique to estimate the polarization-dependent loss (PDL) of reconfigurable optical add-drop multiplexers (ROADMs) in a terrestrial optical network. The idea is to monitor the signal-to-noise ratio (SNR) distribution induced by the PDL and infer the corresponding PDL values through linear regression. The proposed method relies on only the mean and the variance of the SNR distribution, which can be collected by transceivers and sent to a central controller. The PDL regression algorithm and the methodology to acquire the statistical information are presented. We check the method accuracy for different link configurations. We show that our technique well predicts the ROADMs PDL obtaining an 80% uncertainty cut compared to the worst-case values provided by the datasheet for a ROADM after the transmitter and 40% for a ROADM in transit. We investigate two realistic light paths (LPs) of a network in the linear regime showing that the proposed PDL estimation reduces network SNR margins by more than 0.2 dB on these links. We also show that the nonlinear Kerr effect does not reduce the effectiveness of the method.