Modeling EDFA Gain Ripple and Filter Penalties With Machine Learning for Accurate QoT Estimation

Mahajan, Ankush; Christodoulopoulos, K.; Martínez, Ricardo; Spadaro, Salvatore; Muñoz, Raül

doi:10.1109/jlt.2020.2975081

Cited by 54 publications

(32 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the software-defined networking (SDN) controller). Such processing methods are outside the scope of this paper, therefore the reader is referred to [24,25], for various solutions at that processing level. In addition, in this paper we focused our investigation on different transmission aspects, without considering the consequences of the nonlinear interference (NLI) caused by the Kerr effect.…”

Section: Optical Spectral Monitors Placement Scenarios and Spectral Processing Methodsmentioning

confidence: 99%

Spectral processing techniques for efficient monitoring in optical networks

Locatelli

Christodoulopoulos

Moreolo

et al. 2021

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

Having ubiquitous optical monitors in dense wavelength-division multiplexing (DWDM) or flex-grid networks allows the estimation in real time of crucial parameters. Such monitoring would be even more important in disaggregated optical networks, to inspect performance issues related to inter-vendor interoperability. Several important parameters can be retrieved using optical spectrum analyzers (OSAs). However, omnipresent OSAs represents an infeasible solution. Nevertheless, the advent of new, relatively cheap, compact and medium-resolution optical channel monitors (OCMs) enable a more intensive deployment of these devices. In this paper, we identify two main scenarios for the placement of such monitors: at the ingress and at the egress of the optical nodes. In the ingress scenario, we can directly estimate the parameters related to the signals, but not those related to the filters. On the contrary, in the egress scenario, the filter related parameters can be easily detected, but not those related to ASE. Therefore, we present two methods that, leveraging a curve fitting and a machine learning (ML) regression algorithm, allow to detect the missing parameters. We verify the proposed solutions with spectral data acquired in simulation and experimental setups. We obtained good estimation accuracy for both setups and for both studied placement scenarios. Noteworthy, in the experimental assessment of the ingress scenario, we achieved a maximum absolute error (MAE) lower than 1 GHz in filter bandwidth estimation and a MAE lower than 0.5 GHz in filter frequency shift estimation. In addition, by comparing the relative errors of the considered parameters, we identified the ingress scenario as the more beneficial. In particular, we estimated the filter central frequency shift with 84% and the filter 6-dB bandwidth with 75% higher accuracy, with respect to datasheet/reference values. This translates into a total reduction of the estimated signal-to-noise ratio (SNR) penalty, introduced by a single optical filter, of 0.24 dB.

show abstract

Section: Optical Spectral Monitors Placement Scenarios and Spectral Processing Methodsmentioning

confidence: 99%

Spectral processing techniques for efficient monitoring in optical networks

Locatelli

Christodoulopoulos

Moreolo

et al. 2021

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Focusing specifically on the quantification of EDFA uncertainties for margin reduction purposes, ML has previously been utilized to model EDFA gain [34], [35], noise figures [36], [37] and power excursions [38], [39], with [39] further demonstrating wavelength assignment using an algorithm that was able to recommend channel provisioning based upon the ML model results. Correction for EDFA gain ripple has also been targeted in [40], [41], with [41] further using monitoring information to significantly reduce the margin of a network planning tool based upon the Gaussian noise (GN) model. Some recent works have moved beyond predicting ASE noise contributions in isolation; a hybrid approach is investigated in [42], demonstrating that the performance of common ML implementations may be enhanced by inclusion of an analytical model of EDFA gain.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Lightpath QoT Computation With Machine Learning in Partially Disaggregated Optical Networks

D’Amico

Straullu

Borraccini

et al. 2021

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Increasing traffic demands are causing network operators to adopt disaggregated and open networking solutions to better exploit optical transmission capacity, and consequently enable a softwaredefined networking (SDN) approach to control and management that encompasses the WDM data transport layer. In these frameworks, a quality of transmission estimator (QoT-E) that gives the generalized signalto-noise ratio (GSNR) is commonly used to compute the feasibility of transparent lightpaths (LP)s, taking into account the amplified spontaneous emission (ASE) noise and the nonlinear interference (NLI). In general, the ASE noise is the main contributor to the GSNR and is also the most challenging noise component to evaluate in a scenario with varying spectral loads, due to fluctuations in the optical amplifier responses. In this work, we propose a machine learning (ML) algorithm that is trained using different ASE-shaped spectral loads in order to predict the OSNR component of the GSNR; this methodology is subsequently used in combination with a QoT-E in the lightpath computation engine (L-PCE). We present an experiment on a point-to-point optical line system (OLS), including 9 commercial erbium-doped fiber amplifiers (EDFA)s used as black-boxes, each with variable gain and tilt values, and 8 fibers that are characterized by distinct physical parameters. Within this experiment, we receive the signal at the end of the OLS, measuring the bit-error-rate (BER) and the power spectrum, over 2520 different spectral loads. From this dataset, we extract the expected GSNRs and their linear and nonlinear components. Through joint application of a ML algorithm and the open-source GNPy library, we obtain a complete QoT-E, demonstrating that a reliable and accurate LP feasibility predictor may be implemented.INDEX TERMS Machine learning, optical communications, erbium doped fiber amplifier (EDFA), Raman scattering, quality of transmission (QoT).

show abstract

“…The Gaussian Noise (GN) model has been introduced and shown to be quite accurate, while its approximated closed form analytical version combines both good accuracy and low computational complexity [21]. Since then, the GN model became the first choice as PLM for many research works [6], [16]- [18], [24]. Several works explored the estimation of the filtering penalty induced at the ROADM nodes [24], [26].…”

Section: Related Workmentioning

confidence: 99%

Impact of Multi-Vendor Transponders Performance on Design Margin in Optical Networks

et al. 2021

Self Cite

View full text Add to dashboard Cite

For reliable and efficient network planning and operation, accurate estimation of Quality of Transmission (QoT) is necessary. In optical networks, a physical layer model (PLM) is typically used as a QoT estimation tool (Qtool) including a design margin to account for modeling and parameter inaccuracies, to ensure acceptable performance. Such margin also covers the performance variations of the transponders (TPs) which are relatively low in a single vendor environment. However, for disaggregated networks that utilize TPs from multiple vendors, such as partial disaggregated networks with open line system (OLS), this traditional approach limits the Qtool estimation accuracy. Although higher TP performance variations can be covered with an additional margin, this approach would reduce the efficiency and consume the benefits of disaggregation. Therefore, we propose PLM extensions that capture the performance variations of multi-vendor TPs. In particular, we propose four TP vendor dependent performance factors and we also devise a Machine Learning (ML) scheme to learn these performance factors in offline and online network planning scenarios. The proposed extended PLM and ML training scheme are evaluated through realistic simulations. Results show a design margin reduction of greater than 1 dB for new connection requests in a disaggregated network with TPs from four vendors. On top of this, the results also show a ~0.5 dB additional Signal to Noise Ratio (SNR) saving for new connection requests by proper selection of the TPs.

show abstract

Modeling EDFA Gain Ripple and Filter Penalties With Machine Learning for Accurate QoT Estimation

Cited by 54 publications

References 41 publications

Spectral processing techniques for efficient monitoring in optical networks

Spectral processing techniques for efficient monitoring in optical networks

Enhancing Lightpath QoT Computation With Machine Learning in Partially Disaggregated Optical Networks

Impact of Multi-Vendor Transponders Performance on Design Margin in Optical Networks

Contact Info

Product

Resources

About