Dynamic mitigation of EDFA power excursions with machine learning

Huang, Yishen; Gutterman, Craig L.; Samadi, Payman; Cho, Patricia B.; Samoud, Wiem; Ware, Cedric; Lourdiane, Mounia; Zussman, Gil; Bergman, Keren

doi:10.1364/OE.25.002245

Title: Dynamic mitigation of EDFA power excursions with machine learning

Abstract

Dynamic optical networking has promising potential to support the rapidly changing traffic demands in metro and long-haul networks. However, the improvement in dynamicity is hindered by wavelength-dependent power excursions in gain-controlled erbium doped fiber amplifiers (EDFA) when channels change rapidly. We introduce a general approach that leverages machine learning (ML) to characterize and mitigate the power excursions of EDFA systems with different equipment and scales. An ML engine is developed and experimentally validated to show accurate predictions of the power dynamics in cascaded EDFAs. Recommended channel provisioning based on the ML predictions achieves within 1% error of the lowest possible power excursion over 94% of the time. In conclusion, we also showcase significant mitigation of EDFA power excursions in super-channel provisioning when compared to the first-fit wavelength assignment algorithm.

Authors:

Huang, Yishen ^[1]; Gutterman, Craig L. ^[1]; Samadi, Payman ^[1]; Cho, Patricia B. ^[1]; Samoud, Wiem ^[2]; Ware, Cedric ^[3]; Lourdiane, Mounia ^[4]; Zussman, Gil ^[1]; Bergman, Keren ^[1]

Columbia Univ., New York, NY (United States). Dept. of Electrical Engineering
Univ. Paris-Saclay, Paris (France). Telecom ParisTech; Univ. Paris-Saclay, Evry (France). Telecom SudParis
Univ. Paris-Saclay, Paris (France). Telecom ParisTech
Univ. Paris-Saclay, Evry (France). Telecom SudParis

Publication Date:: Fri Jan 27 00:00:00 EST 2017

Research Org.:: Columbia Univ., New York, NY (United States)

Sponsoring Org.:: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)

OSTI Identifier:: 1463689

Grant/Contract Number:: SC0015867

Resource Type:: Accepted Manuscript

Journal Name:: Optics Express

Additional Journal Information:: Journal Volume: 25; Journal Issue: 3; Journal ID: ISSN 1094-4087

Publisher:: Optical Society of America (OSA)

Country of Publication:: United States

Language:: English

Subject:: 97 MATHEMATICS AND COMPUTING; optical communications; fiber optics amplifiers and oscillators; networks; wavelength assignment

Citation Formats


                    Huang, Yishen, Gutterman, Craig L., Samadi, Payman, Cho, Patricia B., Samoud, Wiem, Ware, Cedric, Lourdiane, Mounia, Zussman, Gil, and Bergman, Keren. Dynamic mitigation of EDFA power excursions with machine learning.  United States: N. p., 2017. 
Web.  doi:10.1364/OE.25.002245.

Copy to clipboard


                    Huang, Yishen, Gutterman, Craig L., Samadi, Payman, Cho, Patricia B., Samoud, Wiem, Ware, Cedric, Lourdiane, Mounia, Zussman, Gil, & Bergman, Keren. Dynamic mitigation of EDFA power excursions with machine learning.  United States.  https://doi.org/10.1364/OE.25.002245

Copy to clipboard


                    Huang, Yishen, Gutterman, Craig L., Samadi, Payman, Cho, Patricia B., Samoud, Wiem, Ware, Cedric, Lourdiane, Mounia, Zussman, Gil, and Bergman, Keren. Fri .  
"Dynamic mitigation of EDFA power excursions with machine learning".  United States.  https://doi.org/10.1364/OE.25.002245.  https://www.osti.gov/servlets/purl/1463689.

Copy to clipboard


                    
@article{osti_1463689,

  title        = {Dynamic mitigation of EDFA power excursions with machine learning},

  author       = {Huang, Yishen and Gutterman, Craig L. and Samadi, Payman and Cho, Patricia B. and Samoud, Wiem and Ware, Cedric and Lourdiane, Mounia and Zussman, Gil and Bergman, Keren},

  abstractNote = {Dynamic optical networking has promising potential to support the rapidly changing traffic demands in metro and long-haul networks. However, the improvement in dynamicity is hindered by wavelength-dependent power excursions in gain-controlled erbium doped fiber amplifiers (EDFA) when channels change rapidly. We introduce a general approach that leverages machine learning (ML) to characterize and mitigate the power excursions of EDFA systems with different equipment and scales. An ML engine is developed and experimentally validated to show accurate predictions of the power dynamics in cascaded EDFAs. Recommended channel provisioning based on the ML predictions achieves within 1% error of the lowest possible power excursion over 94% of the time. In conclusion, we also showcase significant mitigation of EDFA power excursions in super-channel provisioning when compared to the first-fit wavelength assignment algorithm.},

  doi          = {10.1364/OE.25.002245},

  journal      = {Optics Express},

  number       = 3,

  volume       = 25,

  place        = {United States},

  year         = {Fri Jan 27 00:00:00 EST 2017},

  month        = {Fri Jan 27 00:00:00 EST 2017}

}

Copy to clipboard

Journal Article:

Free Publicly Available Full Text

Accepted Manuscript (DOE)

Publisher's Version of Record

https://doi.org/10.1364/OE.25.002245

Other availability

Search WorldCat to find libraries that may hold this journal

Citation Metrics:

Cited by: 29 works

Citation information provided by
Web of Science

Save / Share:

Export Metadata

Save to My Library

Works referenced in this record:

Excursion-Free Dynamic Wavelength Switching in Amplified Optical Networks
journal, January 2015

Ahsan, Atiyah S.; Browning, Colm; Wang, Michael S.
Journal of Optical Communications and Networking, Vol. 7, Issue 9
DOI: 10.1364/JOCN.7.000898

Spectrum-efficient and scalable elastic optical path network: architecture, benefits, and enabling technologies
journal, November 2009

Jinno, M.; Takara, H.; Kozicki, B.
IEEE Communications Magazine, Vol. 47, Issue 11
DOI: 10.1109/MCOM.2009.5307468

Software-defined optical network for metro-scale geographically distributed data centers
journal, January 2016

Samadi, Payman; Wen, Ke; Xu, Junjie
Optics Express, Vol. 24, Issue 11
DOI: 10.1364/OE.24.012310

EDFA transient response to channel loss in WDM transmission system
journal, March 1997

Srivastava, A. K.; Sun, Y.; Zyskind, J. L.
IEEE Photonics Technology Letters, Vol. 9, Issue 3
DOI: 10.1109/68.556082

Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers
journal, August 2003

Cechan Tian, ; Kinoshita, S.
Journal of Lightwave Technology, Vol. 21, Issue 8
DOI: 10.1109/JLT.2003.815649

Channel Power Excursions From Single-Step Channel Provisioning
journal, January 2012

Junio, Joseph; Kilper, Daniel C.; Chan, Vincent W. S.
Journal of Optical Communications and Networking, Vol. 4, Issue 9
DOI: 10.1364/JOCN.4.0000A1

Cognitive Dynamic Optical Networks [Invited]
journal, January 2013

de Miguel, Ignacio; Durán, Ramón J.; Jiménez, Tamara
Journal of Optical Communications and Networking, Vol. 5, Issue 10
DOI: 10.1364/JOCN.5.00A107

Works referencing / citing this record:

Deep-Neural-Network-Based Wavelength Selection and Switching in ROADM Systems
journal, January 2018

Mo, Weiyang; Gutterman, Craig L.; Li, Yao
Journal of Optical Communications and Networking, Vol. 10, Issue 10
DOI: 10.1364/jocn.10.0000d1

Deep learning based adaptive sequential data augmentation technique for the optical network traffic synthesis
journal, January 2019

Li, Jin; Wang, Danshi; Li, Shuai
Optics Express, Vol. 27, Issue 13
DOI: 10.1364/oe.27.018831

Optical spectrum feature analysis and recognition for optical network security with machine learning
journal, January 2019

Li, Yanlong; Hua, Nan; Li, Jiading
Optics Express, Vol. 27, Issue 17
DOI: 10.1364/oe.27.024808

Similar Records in DOE PAGES and OSTI.GOV collections:

Power Excursion Mitigation for Flexgrid Defragmentation With Machine Learning

Journal Article Huang, Yishen ; Cho, Patricia B. ; Samadi, Payman ; ... - Journal of Optical Communications and Networking

Flexgrid optical networking relies on spectrum defragmentation to groom channel wavelengths and improve spectral efficiency. Various defragmentation methods—hop, make-before-break, and sweep—interact with the power dynamics of erbium-doped fiber amplifiers (EDFA) differently and result in undesired power excursions that exacerbate the post-EDFA power variance. Here we present a machine learning engine that characterizes the channel dependence of power excursions from historical data. We further demonstrate that post-EDFA power variance during hop, make-before-break, and sweep defragmentation methods can be greatly mitigated by the trained machine learning engine with automated and expedited power adjustment predictions.
Cited by 11
https://doi.org/10.1364/jocn.10.000a69

Full Text Available
Cyber risk assessment and investment optimization using game theory and ML-based anomaly detection and mitigation for wide-area control in smart grids

Other Hyder, Burhan

The electric power grid is increasingly becoming susceptible to cyber attacks that exploit vulnerabilities in the smart grid control, information, and physical layers. Successful cyber attacks can have catastrophic impacts on the social and economic well-being of any nation all over the globe. It has, thus, become imperative to secure the smart grid against such adversarial actions to ensure stable, secure, and reliable operation of the grid. The existing research and industry practices prove to be inadequate in terms of providing pragmatic and effective defense methodologies and measures for long-term cybersecurity planning and real-time cybersecurity for grid operation. For example,more »« less
Artificial Neural Network Representation of Dynamic Criticality Excursion Experiment Data

Journal Article Angelo, Peter L. - Transactions of the American Nuclear Society

This paper outlines time dependent considerations in applying the artificial neural network (ANN) paradigm to dynamic nuclear criticality excursion experiment data. The ANN amongst a variety of uses, can apply to function fitting of multiple input-multiple output data sets, pattern recognition, cluster analysis, and time series prediction. The ANN is a component of Machine Learning (ML) data analysis. The practical application of ML to criticality safety has been funded through the Y-12 Plant Directed Research and Demonstration (PDRD) program to support criticality safety and emergency planning efforts. The initial effort considered function fitting of criticality excursion data. Recent efforts successfullymore »« less
TURBO: Terabits/s Using Reconfigurable Bandwidth Optics (Final Report)

Technical Report Kilper, Daniel ; Bergman, Keren

Large scale, big science applications are generating petabytes of data that need to be shared among multiple locations. Moving a petabyte of data at 100 Gb/s takes 22 hours. Reducing this to single digit hours or below is clearly attractive and with future applications anticipating exabyte scale transfers, multi-terabit per second capacities are needed. This scale of capacity is available using optical systems. Core optical systems have aggregate per fiber capacities on the order of 10 Tb/s and more than 100 Tb/s system experiments have been realized in the lab. But large optical capacities are not just reserved for themore »« less
https://doi.org/10.2172/1618041

Full Text Available
Subcarrier multiplexing with dispersion reduction and direct detection

Patent Sargis, P D ; Haigh, R E ; McCammon, K G

An SCM system is disclosed for simultaneously reducing the concomitant problems of receiver complexity and dispersion penalty and without requiring the use of an expensive, high-bandwidth optical detector. The system provides both a dispersion reduction and a direct detection to the receiver, with microwave mixers and lithium niobate external modulators that produce sidebands that are only separated by a few gigahertz from a principal laser optical carrier. Digital data streams are independently impressed upon these sidebands for transmission over an ordinary single-mode fiber. Independent high-speed data streams are upconverted to microwave frequencies. These subcarriers are then combined with a microwavemore »« less

Similar Records

Title: Dynamic mitigation of EDFA power excursions with machine learning

Abstract

Citation Formats

Excursion-Free Dynamic Wavelength Switching in Amplified Optical Networks journal, January 2015

Spectrum-efficient and scalable elastic optical path network: architecture, benefits, and enabling technologies journal, November 2009

Software-defined optical network for metro-scale geographically distributed data centers journal, January 2016

EDFA transient response to channel loss in WDM transmission system journal, March 1997

Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers journal, August 2003

Channel Power Excursions From Single-Step Channel Provisioning journal, January 2012

Cognitive Dynamic Optical Networks [Invited] journal, January 2013

Deep-Neural-Network-Based Wavelength Selection and Switching in ROADM Systems journal, January 2018

Deep learning based adaptive sequential data augmentation technique for the optical network traffic synthesis journal, January 2019

Optical spectrum feature analysis and recognition for optical network security with machine learning journal, January 2019

Excursion-Free Dynamic Wavelength Switching in Amplified Optical Networks
journal, January 2015

Spectrum-efficient and scalable elastic optical path network: architecture, benefits, and enabling technologies
journal, November 2009

Software-defined optical network for metro-scale geographically distributed data centers
journal, January 2016

EDFA transient response to channel loss in WDM transmission system
journal, March 1997

Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers
journal, August 2003

Channel Power Excursions From Single-Step Channel Provisioning
journal, January 2012

Cognitive Dynamic Optical Networks [Invited]
journal, January 2013

Deep-Neural-Network-Based Wavelength Selection and Switching in ROADM Systems
journal, January 2018

Deep learning based adaptive sequential data augmentation technique for the optical network traffic synthesis
journal, January 2019

Optical spectrum feature analysis and recognition for optical network security with machine learning
journal, January 2019