Machine Learning Assisted EDFA Gain Ripple Modelling for Accurate QoT Estimation

Mahajan, Ankush; Christodoulopoulos, K.; Rivera, Ricardo Victor Martínez; Spadaro, Salvatore; Gonzalez, Raul

doi:10.1049/cp.2019.0984

Cited by 9 publications

(18 citation statements)

References 12 publications

(11 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…11 (c) the results we obtained with our previous work [28]. In [28] we assume electrical SNR monitors available at each ROADM node, which is a quite strong assumption. With [28] we obtained a reduction of the high margin to 0.08dB, that is ~0.92dB improved accuracy.…”

Section: Resultsmentioning

confidence: 84%

“…For comparison purposes we also plot in Fig. 11 (c) the results we obtained with our previous work [28]. In [28] we assume electrical SNR monitors available at each ROADM node, which is a quite strong assumption.…”

Section: Resultsmentioning

confidence: 97%

“…7, we also indicate the DGEs location that flatten the EDFA gain ripples before every ROADM node, that is, at the end of each link. We also assume that we can monitor the feedback power profiles of the DGEs and also the electrical SNR information at the coherent Rx at the transmission endpoints [27], [28]. Finally, we assume that all monitoring information is made available through a suitable control plane.…”

Section: Machine Learning Based Modelingmentioning

confidence: 99%

“…Using OPMs we can extract information and train ML (supervised) models for better understanding of the actual physical condition. In our previous work [28], with the help of electrical SNR monitors at each node, we accurately estimated the gain ripple penalties for new connections requests. Extending our previous work, in this paper, we only use optical data (OPMs) at intermediate nodes and electrical SNR monitoring at the coherent receivers.…”

mentioning

confidence: 99%

See 3 more Smart Citations

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

Mahajan

Christodoulopoulos²,

Martínez³

et al. 2020

J. Lightwave Technol.

View full text Add to dashboard Cite

For reliable and efficient network planning and operation, accurate estimation of Quality of Transmission (QoT) before establishing or reconfiguring the connection is necessary. In optical networks, a design margin is generally included in a QoT estimation tool (Qtool) to account for modeling and parameter inaccuracies, ensuring the acceptable performance. In this work, we use monitoring information from an operating network combined with supervised machine learning (ML) techniques to understand the network conditions. In particular, we model the penalties generated due to i.) Erbium Doped Fiber Amplifier (EDFA) gain ripple effect, and ii.) filter spectral shape uncertainties at Reconfigurable Optical Add and Drop Multiplexer (ROADM) nodes. Enhancing the Qtool with the proposed ML regression models yields estimates for new or reconfigured connections that account for these two effects, resulting in more accurate QoT estimation and a reduced design margin. We initially propose two supervised ML regression models, implemented with Support Vector Machine Regression (SVMR), to estimate the individual penalties of the two effects and then a combined model. On Deutsche Telekom (DT) network topology with 12 nodes and 40 bidirectional links, we achieve a design margin reduction of ~1dB for new connection requests.

show abstract

Section: Resultsmentioning

confidence: 84%

Section: Resultsmentioning

confidence: 97%

Section: Machine Learning Based Modelingmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

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

Mahajan

Christodoulopoulos²,

Martínez³

et al. 2020

J. Lightwave Technol.

View full text Add to dashboard Cite

show abstract

“…Wavelength dependent gain in EDFAs is a significant source of variation and uncertainty in channel performance estimation. Recently there has been much interest in developing machine learning based models to account for the detailed EDFA behavior [1][2][3], replacing lookup tables or analytical models [4][5][6][7][8][9]. However, these machine learning models are built solely from a-posteriori knowledge which is trained from the experimental data, ignoring the existing a-priori knowledge.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Machine Learning EDFA Model

Zhu

Gutterman

Montiel

et al. 2020

Optical Fiber Communication Conference (OFC) 2020

View full text Add to dashboard Cite

show abstract

An overview of ML-based applications for next generation optical networks

Gao

Liu

et al. 2020

Sci. China Inf. Sci.

View full text Add to dashboard Cite

Over the past few decades, the demand for the capacity and reliability of optical networks has continued to grow. In the meantime, optical networks with larger knowledge scales have become sources of numerous heterogeneous data. In order to handle these new challenges, many issues need to be resolved, among which the low-margin optical networks design, power optimization, routing and wavelength assignment (RWA), failure management are quite important. However, the use of traditional algorithms in the above four applications shows some shortcomings. Fortunately, artificial intelligence (AI), especially machine learning (ML), is regarded as one of the most promising methods to overcome these shortcomings. In this study, we review the applications of ML methods in solving these four issues. Although many ML-based researches have emerged, the applications of ML techniques in optical networks still face challenges. Therefore, we also discuss some possible future directions of investigating ML-based approaches in optical networks.

show abstract

Machine Learning Assisted EDFA Gain Ripple Modelling for Accurate QoT Estimation

Abstract: Wavelength dependent EDFA gain ripple has an impact on connection's OSNR performance. We propose a machine learning regression model to estimate the end to end gain ripple penalty and to increase QoT estimation accuracy.

Cited by 9 publications

References 12 publications

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

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

Hybrid Machine Learning EDFA Model

An overview of ML-based applications for next generation optical networks

Contact Info

Product

Resources

About