Dynamic mitigation of EDFA power excursions with machine learning

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

doi:10.1364/OE.25.002245

Dynamic mitigation of EDFA power excursions with machine learning

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

Optics Express
Vol. 25,
Issue 3,
pp. 2245-2258
(2017)
•https://doi.org/10.1364/OE.25.002245

Get Citation
Copy Citation Text
Yishen Huang, Craig L. Gutterman, Payman Samadi, Patricia B. Cho, Wiem Samoud, Cédric Ware, Mounia Lourdiane, Gil Zussman, and Keren Bergman, "Dynamic mitigation of EDFA power excursions with machine learning," Opt. Express 25, 2245-2258 (2017)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Get PDF (2972 KB)
Set citation alerts
Save article

Related Topics
Table of Contents Category
- Optical Communications
Optics & Photonics Topics
?

The topics in this list come from the OSA Optics and Photonics Topics applied to this article.
Previously assigned OCIS codes
- Fiber optics amplifiers and oscillators (060.2320)
- Optical communications (060.4510)
- Networks, wavelength assignment (060.4264)

About this Article
History
- Original Manuscript: November 28, 2016
- Revised Manuscript: January 19, 2017
- Manuscript Accepted: January 20, 2017
- Published: January 27, 2017

Accessible

Open Access

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. We also showcase significant mitigation of EDFA power excursions in super-channel provisioning when compared to the first-fit wavelength assignment algorithm.

Full Article | PDF Article

OSA Recommended Articles

Power Excursion Mitigation for Flexgrid Defragmentation With Machine Learning

Yishen Huang, Patricia B. Cho, Payman Samadi, and Keren Bergman
J. Opt. Commun. Netw. 10(1) A69-A76 (2018)

Excursion-Free Dynamic Wavelength Switching in Amplified Optical Networks

Atiyah S. Ahsan, Colm Browning, Michael S. Wang, Keren Bergman, Daniel C. Kilper, and Liam P. Barry
J. Opt. Commun. Netw. 7(9) 898-905 (2015)

Deep-Neural-Network-Based Wavelength Selection and Switching in ROADM Systems

Weiyang Mo, Craig L. Gutterman, Yao Li, Shengxiang Zhu, Gil Zussman, and Daniel C. Kilper
J. Opt. Commun. Netw. 10(10) D1-D11 (2018)

References

View by:
Article Order
|
Year
|
Author
|
Publication

A. S. Ahsan, C. Browning, M. S. Wang, K. Bergman, D. C. Kilper, and L. P. Barry, “Excursion-free dynamic wavelength switching in amplified optical networks,” J. Opt. Commun. Netw. 7(9), 898–905 (2015).
[Crossref]
M. Fiorani, P. Samadi, Y. Shen, L. Wosinska, and K. Bergman, “Flexible architecture and control strategy for metro-scale networking of geographically distributed data centers,” in European Conference and Exhibition on Optical Communication (2016).
M. Jinno, H. Takara, B. Kozicki, Y. Tsukishima, Y. Sone, and S. Matsuoka, “Spectrum-efficient and scalable elastic optical path network: architecture, benefits, and enabling technologies,” IEEE Commun. Mag. 47(11), 66–73 (2009).
[Crossref]
P. Samadi, K. Wen, J. Xu, and K. Bergman, “Software-defined optical network for metro-scale geographically distributed data centers,” Opt. Express 24(11), 12310–12320 (2016).
[Crossref] [PubMed]
P. Samadi, J. Xu, K. Wen, H. Guan, Z. Li, and K. Bergman, “Experimental demonstration of converged inter / intra data center network architecture,” in 17th International Conference on Transparent Optical Networks (2015).
[Crossref]
D. C. Kilper, M. Bhopalwala, H. Rastegarfar, and W. Mo, “Optical power dynamics in wavelength layer software defined networking,” in Advanced Photonics (2015).
A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]
C. Tian and S. Kinoshita, “Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers,” J. Lightwave Technol. 21(8), 1728–1734 (2003).
[Crossref]
D. A. Mongardien, S. Borne, C. Martinelli, C. Simonneau, and D. Bayart, “Managing channels add/drop in flexible networks based on hybrid raman / Erbium amplified spans,” in European Conference and Exhibition on Optical Communication (2006).
[Crossref]
E. A. Barboza, C. J. A. Bastos-filho, J. F. Martins-Filho, U. C. de Moura, and J. R. F. de Oliveira, “Self-adaptive Erbium-doped fiber amplifiers using machine learning,” in International Microwave & Optoelectronics Conference (2013).
P. J. Lin, “Reducing optical power variation in amplified optical network,” in International Conference on Communication Technology (2003).
[Crossref]
N. Sambo, F. Cugini, G. Bottari, P. Iovanna, and P. Castoldi, “Routing and spectrum assignment for super-channels in flex-grid optical networks,” in European Conference and Exhibition on Optical Communication (2012).
[Crossref]
J. Junio, D. C. Kilper, and V. W. S. Chan, “Channel power excursions from single-step channel provisioning,” J. Opt. Commun. Netw. 4(9), A1–A7 (2012).
[Crossref]
K. Ishii, J. Kurumida, and S. Namiki, “Wavelength assignment dependency of AGC EDFA gain offset under dynamic optical circuit switching,” in Optical Fiber Communication Conference (2014).
[Crossref]
I. de Miguel, R. J. Durán, T. Jiménez, N. Fernández, J. C. Aguado, R. M. Lorenzo, A. Caballero, I. T. Monroy, Y. Ye, A. Tymecki, I. Tomkos, M. Angelou, D. Klonidis, A. Francescon, D. Siracusa, and E. Salvadori, “Cognitive dynamic optical networks,” J. Opt. Commun. Netw. 5(10), A107–A118 (2013).
[Crossref]
Y. Huang, W. Samoud, C. L. Gutterman, C. Ware, M. Lourdiane, G. Zussman, P. Samadi, and K. Bergmen, “A machine learning approach for dynamic optical channel add / drop strategies that minimize EDFA power excursions,” in European Conference and Exhibition on Optical Communication (2016).
U. Moura, M. Garrich, H. Carvalho, M. Svolenski, A. Andrade, F. Margarido, A. C. Cesar, E. Conforti, and J. Oliveira, “SDN-enabled EDFA gain adjustment cognitive methodology for dynamic optical networks,” in European Conference and Exhibition on Optical Communication (2015).
[Crossref]
C. M. Bishop, Pattern Recognition and Machine Learning (Springer, 2007).
J. D. Reis, M. Garrich, D. M. Pataca, J. C. M. Diniz, V. N. Rozental, L. H. H. Carvalho, E. C. Magalhães, U. Moura, N. G. Gonzalez, J. R. F. Oliveira, and J. C. R. F. Oliveira, “Flexible optical transmission systems for future networking,” in International Telecommunications Network Strategy and Planning Symposium (Networks) (2014).
[Crossref]
H. Zang, J. P. Jue, and B. Mukherjee, “A review of routing and wavelength assignment approaches for wavelength-routed optical WDM networks,” Opt. Networks Mag. 1(1), 47–60 (2000).

2009 (1)

M. Jinno, H. Takara, B. Kozicki, Y. Tsukishima, Y. Sone, and S. Matsuoka, “Spectrum-efficient and scalable elastic optical path network: architecture, benefits, and enabling technologies,” IEEE Commun. Mag. 47(11), 66–73 (2009).
[Crossref]

2003 (1)

C. Tian and S. Kinoshita, “Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers,” J. Lightwave Technol. 21(8), 1728–1734 (2003).
[Crossref]

2000 (1)

H. Zang, J. P. Jue, and B. Mukherjee, “A review of routing and wavelength assignment approaches for wavelength-routed optical WDM networks,” Opt. Networks Mag. 1(1), 47–60 (2000).

1997 (1)

A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]

Aguado, J. C.

Ahsan, A. S.

Andrade, A.

U. Moura, M. Garrich, H. Carvalho, M. Svolenski, A. Andrade, F. Margarido, A. C. Cesar, E. Conforti, and J. Oliveira, “SDN-enabled EDFA gain adjustment cognitive methodology for dynamic optical networks,” in European Conference and Exhibition on Optical Communication (2015).
[Crossref]

Angelou, M.

Barry, L. P.

Bayart, D.

D. A. Mongardien, S. Borne, C. Martinelli, C. Simonneau, and D. Bayart, “Managing channels add/drop in flexible networks based on hybrid raman / Erbium amplified spans,” in European Conference and Exhibition on Optical Communication (2006).
[Crossref]

Bergman, K.

M. Fiorani, P. Samadi, Y. Shen, L. Wosinska, and K. Bergman, “Flexible architecture and control strategy for metro-scale networking of geographically distributed data centers,” in European Conference and Exhibition on Optical Communication (2016).

P. Samadi, J. Xu, K. Wen, H. Guan, Z. Li, and K. Bergman, “Experimental demonstration of converged inter / intra data center network architecture,” in 17th International Conference on Transparent Optical Networks (2015).
[Crossref]

Bergmen, K.

Y. Huang, W. Samoud, C. L. Gutterman, C. Ware, M. Lourdiane, G. Zussman, P. Samadi, and K. Bergmen, “A machine learning approach for dynamic optical channel add / drop strategies that minimize EDFA power excursions,” in European Conference and Exhibition on Optical Communication (2016).

Borne, S.

Bottari, G.

N. Sambo, F. Cugini, G. Bottari, P. Iovanna, and P. Castoldi, “Routing and spectrum assignment for super-channels in flex-grid optical networks,” in European Conference and Exhibition on Optical Communication (2012).
[Crossref]

Browning, C.

Caballero, A.

Carvalho, H.

Carvalho, L. H. H.

J. D. Reis, M. Garrich, D. M. Pataca, J. C. M. Diniz, V. N. Rozental, L. H. H. Carvalho, E. C. Magalhães, U. Moura, N. G. Gonzalez, J. R. F. Oliveira, and J. C. R. F. Oliveira, “Flexible optical transmission systems for future networking,” in International Telecommunications Network Strategy and Planning Symposium (Networks) (2014).
[Crossref]

Castoldi, P.

Cesar, A. C.

Chan, V. W. S.

J. Junio, D. C. Kilper, and V. W. S. Chan, “Channel power excursions from single-step channel provisioning,” J. Opt. Commun. Netw. 4(9), A1–A7 (2012).
[Crossref]

Conforti, E.

Cugini, F.

de Miguel, I.

Diniz, J. C. M.

Durán, R. J.

Fernández, N.

Fiorani, M.

Francescon, A.

Garrich, M.

Gonzalez, N. G.

Guan, H.

Gutterman, C. L.

Huang, Y.

Iovanna, P.

Ishii, K.

K. Ishii, J. Kurumida, and S. Namiki, “Wavelength assignment dependency of AGC EDFA gain offset under dynamic optical circuit switching,” in Optical Fiber Communication Conference (2014).
[Crossref]

Jiménez, T.

Jinno, M.

Jue, J. P.

H. Zang, J. P. Jue, and B. Mukherjee, “A review of routing and wavelength assignment approaches for wavelength-routed optical WDM networks,” Opt. Networks Mag. 1(1), 47–60 (2000).

Junio, J.

J. Junio, D. C. Kilper, and V. W. S. Chan, “Channel power excursions from single-step channel provisioning,” J. Opt. Commun. Netw. 4(9), A1–A7 (2012).
[Crossref]

Kilper, D. C.

J. Junio, D. C. Kilper, and V. W. S. Chan, “Channel power excursions from single-step channel provisioning,” J. Opt. Commun. Netw. 4(9), A1–A7 (2012).
[Crossref]

Kinoshita, S.

C. Tian and S. Kinoshita, “Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers,” J. Lightwave Technol. 21(8), 1728–1734 (2003).
[Crossref]

Klonidis, D.

Kozicki, B.

Kurumida, J.

Li, Z.

Lin, P. J.

P. J. Lin, “Reducing optical power variation in amplified optical network,” in International Conference on Communication Technology (2003).
[Crossref]

Lorenzo, R. M.

Lourdiane, M.

Magalhães, E. C.

Margarido, F.

Martinelli, C.

Matsuoka, S.

Mongardien, D. A.

Monroy, I. T.

Moura, U.

Mukherjee, B.

H. Zang, J. P. Jue, and B. Mukherjee, “A review of routing and wavelength assignment approaches for wavelength-routed optical WDM networks,” Opt. Networks Mag. 1(1), 47–60 (2000).

Namiki, S.

Oliveira, J.

Oliveira, J. C. R. F.

Oliveira, J. R. F.

Pataca, D. M.

Reis, J. D.

Rozental, V. N.

Salvadori, E.

Samadi, P.

Sambo, N.

Samoud, W.

Shen, Y.

Simonneau, C.

Siracusa, D.

Sone, Y.

Srivastava, A. K.

A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]

Sulhoff, J. W.

A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]

Sun, Y.

A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]

Svolenski, M.

Takara, H.

Tian, C.

C. Tian and S. Kinoshita, “Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers,” J. Lightwave Technol. 21(8), 1728–1734 (2003).
[Crossref]

Tomkos, I.

Tsukishima, Y.

Tymecki, A.

Wang, M. S.

Ware, C.

Wen, K.

Wosinska, L.

Xu, J.

Ye, Y.

Zang, H.

H. Zang, J. P. Jue, and B. Mukherjee, “A review of routing and wavelength assignment approaches for wavelength-routed optical WDM networks,” Opt. Networks Mag. 1(1), 47–60 (2000).

Zussman, G.

Zyskind, J. L.

A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]

IEEE Commun. Mag. (1)

IEEE Photonics Technol. Lett. (1)

A. K. Srivastava, Y. Sun, J. L. Zyskind, and J. W. Sulhoff, “EDFA transient response to channel loss in WDM transmission system,” IEEE Photonics Technol. Lett. 9(3), 386–388 (1997).
[Crossref]

J. Lightwave Technol. (1)

C. Tian and S. Kinoshita, “Analysis and control of transient dynamics of EDFA pumped by 1480- and 980-nm lasers,” J. Lightwave Technol. 21(8), 1728–1734 (2003).
[Crossref]

J. Opt. Commun. Netw. (3)

J. Junio, D. C. Kilper, and V. W. S. Chan, “Channel power excursions from single-step channel provisioning,” J. Opt. Commun. Netw. 4(9), A1–A7 (2012).
[Crossref]

Opt. Express (1)

Opt. Networks Mag. (1)

H. Zang, J. P. Jue, and B. Mukherjee, “A review of routing and wavelength assignment approaches for wavelength-routed optical WDM networks,” Opt. Networks Mag. 1(1), 47–60 (2000).

Other (12)

D. C. Kilper, M. Bhopalwala, H. Rastegarfar, and W. Mo, “Optical power dynamics in wavelength layer software defined networking,” in Advanced Photonics (2015).

E. A. Barboza, C. J. A. Bastos-filho, J. F. Martins-Filho, U. C. de Moura, and J. R. F. de Oliveira, “Self-adaptive Erbium-doped fiber amplifiers using machine learning,” in International Microwave & Optoelectronics Conference (2013).

P. J. Lin, “Reducing optical power variation in amplified optical network,” in International Conference on Communication Technology (2003).
[Crossref]

C. M. Bishop, Pattern Recognition and Machine Learning (Springer, 2007).

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.

Click here to see a list of articles that cite this paper

Fig. 1 Setup of the multi-span EDFA system; the additional EDFA and VOA in the dashed box are included for the 3-span system.

Download Full Size | PPT Slide | PDF

Fig. 2 Measured post-EDFA power spectra with 24 ON channels for both systems. Channels 1 to 24 correspond to ITU-T C-band 194.40THz to 192.10THz with 100GHz spacing. Channels are launched with uniform power.

Download Full Size | PPT Slide | PDF

Fig. 3 Associated weights assigned to each channel by RR for the 2-span and 3-span EDFA systems, indicating each channel’s contribution to the post-EDFA power discrepancy in respective systems.

Download Full Size | PPT Slide | PDF

Fig. 4 Reduction of the ML models’ prediction MSEs of power STDEV with increasing training data size.

Download Full Size | PPT Slide | PDF

Fig. 5 Comparisons between predictions and measurements of post-EDFA power discrepancy for single-channel add (a) and drop (b). The top four slot options with the lowest predicted power STDEV are circled. (c) and (d) illustrate the good channels to add/drop, and the worst channels to avoid. (e) and (f) compare the post-EDFA power spectra of ON channels between the best and worst cases in channel add and drop, respectively.

Download Full Size | PPT Slide | PDF

Fig. 6 Correlation between the prediction MSE (horizontal axis) and the percentage of accurate recommendations (vertical axis) for KBR and RR for the (a) 2-span and (b) 3-span EDFA systems. The percentage of accurate recommendations reflects the number of tests in which the ML engine correctly recommends the top channels, out of the 200 tests performed.

Download Full Size | PPT Slide | PDF

Fig. 7 CDF of the percent error between the power discrepancy of recommended options and the actual lowest power discrepancy, plotted for single channel candidates based on KBR, RR, and random selections of channels for the (a) 2-span and (b) 3-span EDFA systems. Compared to random selections, ML recommendations with KBR and RR show significant improvement in approaching the lowest possible post-EDFA power discrepancy.

Download Full Size | PPT Slide | PDF

Fig. 8 CDF of the percent error between the power discrepancy of recommended options and the actual lowest power discrepancy, at different training data sizes. (a) and (b) illustrate for the KBR model on the 2-span and 3-span EDFA systems respectively. (c) and (d) illustrate for the RR model on the 2-span and 3-span EDFA systems respectively.

Download Full Size | PPT Slide | PDF

Fig. 9 Functional workflow of the ML engine that enables super-channel addition with the least induced power excursions and post-EDFA power discrepancies.

Download Full Size | PPT Slide | PDF

Fig. 10 Comparisons between predictions and measurements of post-EDFA power discrepancy for super-channel addition consisting of (a) two contiguous sub-channels and (b) three contiguous sub-channels. The top two super-channel candidates with the lowest predicted power STDEV are circled. (c) and (d) illustrate the best, good, and worst super-channel candidates.

Download Full Size | PPT Slide | PDF

Fig. 11 Twenty randomly initialized scenarios to compare the resultant power STDEV values among super-channel additions based on actual measurements, ML predictions, and the first-fit allocation algorithm for (a) two-channel-wide and (b) three-channel-wide super-channels in the 3-span EDFA system.

Download Full Size | PPT Slide | PDF

Fig. 12 Illustration of channel add/drop operations at the intermediate EDFA node.

Download Full Size | PPT Slide | PDF

Tables (1)

Table 1 Time consumption of training and prediction for RR and KBR.

View Table

Equations (5)

Equations on this page are rendered with MathJax. Learn more.

x_{i j}^{p r e p} = \frac{x_{i j} - {\bar{x}}_{j}}{σ_{j}},

y_{i j}^{p r e p} = y_{i j} - {\bar{y}}_{j} .

w_{R R} = \arg \min_{w} ({‖ y - X w ‖}^{2} + λ {‖ w ‖}^{2}),

w_{R R} = {(λ I + X^{T} X)}^{- 1} X^{T} y,

K (x, x') = α \exp (- \frac{1}{b} {‖ x - x' ‖}^{2}),

Model	RR	KBR
Time to train with 600 data points [ms]	82.2	2300
Time to predict for a single scenario [ms]	0.068	467

Abstract

References

2016 (1)

2015 (1)

2013 (1)

2012 (1)

2009 (1)

2003 (1)

2000 (1)

1997 (1)

Aguado, J. C.

Ahsan, A. S.

Andrade, A.

Angelou, M.

Barry, L. P.

Bayart, D.

Bergman, K.

Bergmen, K.

Borne, S.

Bottari, G.

Browning, C.

Caballero, A.

Carvalho, H.

Carvalho, L. H. H.

Castoldi, P.

Cesar, A. C.

Chan, V. W. S.

Conforti, E.

Cugini, F.

de Miguel, I.

Diniz, J. C. M.

Durán, R. J.

Fernández, N.

Fiorani, M.

Francescon, A.

Garrich, M.

Gonzalez, N. G.

Guan, H.

Gutterman, C. L.

Huang, Y.

Iovanna, P.

Ishii, K.

Jiménez, T.

Jinno, M.

Jue, J. P.

Junio, J.

Kilper, D. C.

Kinoshita, S.

Klonidis, D.

Kozicki, B.

Kurumida, J.

Li, Z.

Lin, P. J.

Lorenzo, R. M.

Lourdiane, M.

Magalhães, E. C.

Margarido, F.

Martinelli, C.

Matsuoka, S.

Mongardien, D. A.

Monroy, I. T.

Moura, U.

Mukherjee, B.

Namiki, S.

Oliveira, J.

Oliveira, J. C. R. F.

Oliveira, J. R. F.

Pataca, D. M.

Reis, J. D.

Rozental, V. N.

Salvadori, E.

Samadi, P.

Sambo, N.

Samoud, W.

Shen, Y.

Simonneau, C.

Siracusa, D.

Sone, Y.

Srivastava, A. K.

Sulhoff, J. W.