Abstract

Networks are complex interacting systems involving cloud operations, core and metro transport, and mobile connectivity all the way to video streaming and similar user applications. With localized and highly engineered operational tools, it is typical of these networks to take days to weeks for any changes, upgrades, or service deployments to take effect. Machine learning, a sub-domain of artificial intelligence, is highly suitable for complex system representation. In this tutorial paper, we review several machine learning concepts tailored to the optical networking industry and discuss algorithm choices, data and model management strategies, and integration into existing network control and management tools. We then describe four networking case studies in detail, covering predictive maintenance, virtual network topology management, capacity optimization, and optical spectral analysis.

© 2018 Optical Society of America

Full Article  |  PDF Article
OSA Recommended Articles
Virtual Network Topology Adaptability Based on Data Analytics for Traffic Prediction

Fernando Morales, Marc Ruiz, Lluís Gifre, Luis M. Contreras, Víctor López, and Luis Velasco
J. Opt. Commun. Netw. 9(1) A35-A45 (2017)

Autonomic Disaggregated Multilayer Networking

Lluís Gifre, Jose-Luis Izquierdo-Zaragoza, Marc Ruiz, and Luis Velasco
J. Opt. Commun. Netw. 10(5) 482-492 (2018)

Multilayer Control for Packet-Optical Networks [Invited]

P. Iovanna, A. Germoni, F. Testa, G. Cossu, V. López, and R. Sabella
J. Opt. Commun. Netw. 5(10) A86-A99 (2013)

References

  • View by:
  • |
  • |
  • |

  1. A. Gupta and R. K. Jha, “A survey of 5G network: architecture and emerging technologies,” IEEE Access, vol.  3, pp. 1206–1232, 2015.
    [Crossref]
  2. V. Vusirikala, “A decade of software defined networking at Google,” in European Conf. Optical Communications, Sept. 2018.
  3. D. Rafique, H. Griesser, and J. P. Elbers, “Enabling 64Gbaud coherent optical transceivers,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.
  4. V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.
  5. M. Ruiz and L. Velasco, Provisioning, Recovery, and In Operation Planning in Elastic Optical Networks, Wiley, 2017.
  6. S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed. Upper Saddle River, NJ: Prentice Hall, 2009.
  7. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York, NY: Wiley, 2000.
  8. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd ed. Springer, 2009.
  9. D. Zibar, L. H. H. de Carvalho, M. Piels, A. Doberstein, J. Diniz, B. Nebendahl, C. Franciscangelis, J. Estaran, H. Haisch, N. G. Gonzalez, J. C. R. F. de Oliveira, and I. T. Monroy, “Application of machine learning techniques for amplitude and phase noise characterization,” J. Lightwave Technol., vol.  33, no. 7, pp. 1333–1343, Apr. 2015.
    [Crossref]
  10. Y. Huang, P. B. Cho, P. Samadi, and K. Bergman, “Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.
  11. D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.
  12. D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
    [Crossref]
  13. A. P. Vela, B. Shariati, M. Ruiz, F. Cugini, A. Castro, H. Lu, R. Proietti, J. Comellas, P. Castoldi, S. J. B. Yoo, and L. Velasco, “Soft failure localization during commissioning testing and lightpath operation,” J. Opt. Commun. Netw., vol.  10, no. 1, pp. A27–A36, Jan. 2018.
    [Crossref]
  14. J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
    [Crossref]
  15. F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.
  16. S. Marsland, Machine Learning: An Algorithmic Perspective, CRC Press, 2011.
  17. O. Chapelle, B. Schlkopf, and A. Zien, Semi-Supervised Learning, 1st ed. MIT, 2010.
  18. S. Shahkarami, F. Musumeci, F. Cugini, and M. Tornatore, “Machine-learning-based soft-failure detection and identification in optical networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper M3A.5.
  19. S. B. Kotsiantis, “Supervised machine learning: a review of classification techniques,” in Emerging Artificial Intelligence Applications in Computer Engineering—Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies, IOS, 2007, pp. 3–24.
  20. Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn., vol.  2, no. 1, pp. 1–127, Jan. 2009.
    [Crossref]
  21. F. Morales, M. Ruiz, L. Gifre, L. M. Contreras, V. López, and L. Velasco, “Virtual network topology adaptability based on data analytics for traffic prediction,” J. Opt. Commun. Netw., vol.  9, no. 1, pp. A35–A45, Jan. 2017.
    [Crossref]
  22. S. G. Petridou, P. G. Sarigiannidis, G. I. Papadimitriou, and A. S. Pomportsis, “On the use of clustering algorithms for message scheduling in WDM star networks,” J. Lightwave Technol., vol.  26, no. 17, pp. 2999–3010, Sept. 2008.
    [Crossref]
  23. R. S. Sutton and A. G. Barto, Introduction to Reinforcement Learning, 1st ed. Cambridge, MA: MIT, 1998.
  24. C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol.  8, no. 3, pp. 279–292, May 1992.
    [Crossref]
  25. Y. V. Kiran, T. Venkatesh, and C. S. R. Murthy, “A reinforcement learning framework for path selection and wavelength selection in optical burst switched networks,” IEEE J. Select Areas Commun., vol.  25, no. 9, pp. 18–26, Dec. 2007.
    [Crossref]
  26. S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
    [Crossref]
  27. “gRPC—An RPC library and framework,” GitHub. Inc, 2015 [Online]. Available: https://github.com/grpc/grpc .
  28. E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.
  29. L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
    [Crossref]
  30. R. Casellas, R. Martínez, R. Vilalta, and R. Muñoz, “Control, management, and orchestration of optical networks: evolution, trends, and challenges,” J. Lightwave Technol., vol.  36, no. 7, pp. 1390–1402, Apr. 2018.
    [Crossref]
  31. L. Gifre, J.-L. Izquierdo-Zaragoza, M. Ruiz, and L. Velasco, “Autonomic disaggregated multilayer networking,” J. Opt. Commun. Netw., vol.  10, no. 5, pp. 482–492, May 2018.
    [Crossref]
  32. “TensorFlow–An open source machine learning framework for everyone,” GitHub. Inc, 2018 [Online]. Available: https://www.tensorflow.org/ .
  33. S. R. Tembo, S. Vaton, J. L. Courant, and S. Gosselin, “A tutorial on the EM algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks,” in Int. Wireless Communications and Mobile Computing Conf. (IWCMC), Sept. 2016, pp. 369–376.
  34. D. Rafique, T. Szyrkowiec, A. Autenrieth, and J.-P. Elbers, “Analytics-driven fault discovery and diagnosis for cognitive root cause analysis,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper W4F.6.
  35. F. E. Grubbs, “Sample criteria for testing outlying observations,” Annu. Math. Stat., vol.  21, no. 1, pp. 27–58, Mar. 1950.
    [Crossref]
  36. J. Paparrizos and L. Gravano, “k-shape: efficient and accurate clustering of time series,” SIGMOD Rec., vol.  45, no. 1, pp. 69–76, June 2016.
    [Crossref]
  37. A. P. Vela, M. Ruiz, F. Fresi, N. Sambo, F. Cugini, G. Meloni, L. Potì, L. Velasco, and P. Castoldi, “BER degradation detection and failure identification in elastic optical networks,” J. Lightwave Technol., vol.  35, no. 21, pp. 4595–4604, Nov. 2017.
    [Crossref]
  38. L. Barletta, A. Giusti, C. Rottondi, and M. Tornatore, “QoT estimation for unestablished lighpaths using machine learning,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.
  39. T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.
  40. D. Rafique, “Machine learning based optimal modulation format prediction for physical layer network planning,” in Int. Conf. Transparent Optical Networks, IEEE, 2018, paper Tu.A3.5.
  41. P. Poggiolini, “The GN model of non-linear propagation in uncompensated coherent optical systems,” J. Lightwave Technol., vol.  30, no. 24, pp. 3857–3879, Dec. 2012.
    [Crossref]
  42. T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
    [Crossref]
  43. D. Rafique and A. D. Ellis, “Nonlinear and ROADM induced penalties in 28 Gbaud dynamic optical mesh networks employing electronic signal processing,” Opt. Express, vol.  19, no. 18, pp. 16739–16748, Aug. 2011.
    [Crossref]

2018 (5)

2017 (2)

2016 (1)

J. Paparrizos and L. Gravano, “k-shape: efficient and accurate clustering of time series,” SIGMOD Rec., vol.  45, no. 1, pp. 69–76, June 2016.
[Crossref]

2015 (3)

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

A. Gupta and R. K. Jha, “A survey of 5G network: architecture and emerging technologies,” IEEE Access, vol.  3, pp. 1206–1232, 2015.
[Crossref]

D. Zibar, L. H. H. de Carvalho, M. Piels, A. Doberstein, J. Diniz, B. Nebendahl, C. Franciscangelis, J. Estaran, H. Haisch, N. G. Gonzalez, J. C. R. F. de Oliveira, and I. T. Monroy, “Application of machine learning techniques for amplitude and phase noise characterization,” J. Lightwave Technol., vol.  33, no. 7, pp. 1333–1343, Apr. 2015.
[Crossref]

2014 (1)

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

2012 (1)

2011 (2)

S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
[Crossref]

D. Rafique and A. D. Ellis, “Nonlinear and ROADM induced penalties in 28 Gbaud dynamic optical mesh networks employing electronic signal processing,” Opt. Express, vol.  19, no. 18, pp. 16739–16748, Aug. 2011.
[Crossref]

2009 (1)

Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn., vol.  2, no. 1, pp. 1–127, Jan. 2009.
[Crossref]

2008 (1)

2007 (1)

Y. V. Kiran, T. Venkatesh, and C. S. R. Murthy, “A reinforcement learning framework for path selection and wavelength selection in optical burst switched networks,” IEEE J. Select Areas Commun., vol.  25, no. 9, pp. 18–26, Dec. 2007.
[Crossref]

1992 (1)

C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol.  8, no. 3, pp. 279–292, May 1992.
[Crossref]

1950 (1)

F. E. Grubbs, “Sample criteria for testing outlying observations,” Annu. Math. Stat., vol.  21, no. 1, pp. 27–58, Mar. 1950.
[Crossref]

Autenrieth, A.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
[Crossref]

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

D. Rafique, T. Szyrkowiec, A. Autenrieth, and J.-P. Elbers, “Analytics-driven fault discovery and diagnosis for cognitive root cause analysis,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper W4F.6.

Barletta, L.

L. Barletta, A. Giusti, C. Rottondi, and M. Tornatore, “QoT estimation for unestablished lighpaths using machine learning,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Barto, A. G.

R. S. Sutton and A. G. Barto, Introduction to Reinforcement Learning, 1st ed. Cambridge, MA: MIT, 1998.

Bengio, Y.

Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn., vol.  2, no. 1, pp. 1–127, Jan. 2009.
[Crossref]

Bergman, K.

Y. Huang, P. B. Cho, P. Samadi, and K. Bergman, “Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Bohn, M.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Casellas, R.

Castoldi, P.

Castro, A.

Chamania, M.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Chapelle, O.

O. Chapelle, B. Schlkopf, and A. Zien, Semi-Supervised Learning, 1st ed. MIT, 2010.

Cho, P. B.

Y. Huang, P. B. Cho, P. Samadi, and K. Bergman, “Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Choi, M.-J.

S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
[Crossref]

Clouet, B.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Comellas, J.

Contreras, L. M.

F. Morales, M. Ruiz, L. Gifre, L. M. Contreras, V. López, and L. Velasco, “Virtual network topology adaptability based on data analytics for traffic prediction,” J. Opt. Commun. Netw., vol.  9, no. 1, pp. A35–A45, Jan. 2017.
[Crossref]

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

Courant, J. L.

S. R. Tembo, S. Vaton, J. L. Courant, and S. Gosselin, “A tutorial on the EM algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks,” in Int. Wireless Communications and Mobile Computing Conf. (IWCMC), Sept. 2016, pp. 369–376.

Cugini, F.

A. P. Vela, B. Shariati, M. Ruiz, F. Cugini, A. Castro, H. Lu, R. Proietti, J. Comellas, P. Castoldi, S. J. B. Yoo, and L. Velasco, “Soft failure localization during commissioning testing and lightpath operation,” J. Opt. Commun. Netw., vol.  10, no. 1, pp. A27–A36, Jan. 2018.
[Crossref]

A. P. Vela, M. Ruiz, F. Fresi, N. Sambo, F. Cugini, G. Meloni, L. Potì, L. Velasco, and P. Castoldi, “BER degradation detection and failure identification in elastic optical networks,” J. Lightwave Technol., vol.  35, no. 21, pp. 4595–4604, Nov. 2017.
[Crossref]

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

S. Shahkarami, F. Musumeci, F. Cugini, and M. Tornatore, “Machine-learning-based soft-failure detection and identification in optical networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper M3A.5.

Dayan, P.

C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol.  8, no. 3, pp. 279–292, May 1992.
[Crossref]

de Carvalho, L. H. H.

de Miguel, I.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

de Oliveira, J. C. R. F.

de Waardt, H.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Diniz, J.

Doberstein, A.

Duda, R. O.

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York, NY: Wiley, 2000.

Durán, R. J.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

Elbers, J. P.

D. Rafique, H. Griesser, and J. P. Elbers, “Enabling 64Gbaud coherent optical transceivers,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Elbers, J.-P.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
[Crossref]

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.

D. Rafique, T. Szyrkowiec, A. Autenrieth, and J.-P. Elbers, “Analytics-driven fault discovery and diagnosis for cognitive root cause analysis,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper W4F.6.

Ellis, A. D.

Estaran, J.

Fernandez-Palacios, J. P.

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Ferraris, G.

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

Franciscangelis, C.

Fresi, F.

Friedman, J.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd ed. Springer, 2009.

Gerstel, O.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Gifre, L.

Giusti, A.

L. Barletta, A. Giusti, C. Rottondi, and M. Tornatore, “QoT estimation for unestablished lighpaths using machine learning,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Gonzalez, N. G.

Gosselin, S.

S. R. Tembo, S. Vaton, J. L. Courant, and S. Gosselin, “A tutorial on the EM algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks,” in Int. Wireless Communications and Mobile Computing Conf. (IWCMC), Sept. 2016, pp. 369–376.

Gran, J. M.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Gravano, L.

J. Paparrizos and L. Gravano, “k-shape: efficient and accurate clustering of time series,” SIGMOD Rec., vol.  45, no. 1, pp. 69–76, June 2016.
[Crossref]

Grießer, H.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
[Crossref]

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.

Griesser, H.

D. Rafique, H. Griesser, and J. P. Elbers, “Enabling 64Gbaud coherent optical transceivers,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Grubbs, F. E.

F. E. Grubbs, “Sample criteria for testing outlying observations,” Annu. Math. Stat., vol.  21, no. 1, pp. 27–58, Mar. 1950.
[Crossref]

Gupta, A.

A. Gupta and R. K. Jha, “A survey of 5G network: architecture and emerging technologies,” IEEE Access, vol.  3, pp. 1206–1232, 2015.
[Crossref]

Haisch, H.

Hart, P. E.

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York, NY: Wiley, 2000.

Hastie, T.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd ed. Springer, 2009.

Hong, J. W.-K.

S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
[Crossref]

Hoshida, T.

T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.

Huang, Y.

Y. Huang, P. B. Cho, P. Samadi, and K. Bergman, “Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Izquierdo-Zaragoza, J.-L.

Jha, R. K.

A. Gupta and R. K. Jha, “A survey of 5G network: architecture and emerging technologies,” IEEE Access, vol.  3, pp. 1206–1232, 2015.
[Crossref]

Jimenez, R.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Jukan, A.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

Kato, T.

T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.

Kiran, Y. V.

Y. V. Kiran, T. Venkatesh, and C. S. R. Murthy, “A reinforcement learning framework for path selection and wavelength selection in optical burst switched networks,” IEEE J. Select Areas Commun., vol.  25, no. 9, pp. 18–26, Dec. 2007.
[Crossref]

Klonidis, D.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Kotsiantis, S. B.

S. B. Kotsiantis, “Supervised machine learning: a review of classification techniques,” in Emerging Artificial Intelligence Applications in Computer Engineering—Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies, IOS, 2007, pp. 3–24.

Kuschnerov, M.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Laredo, J.

E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.

Lobato, I.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Lopez, V.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

López, V.

Lu, H.

Macaluso, I.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

Marsland, S.

S. Marsland, Machine Learning: An Algorithmic Perspective, CRC Press, 2011.

Mårtensson, J.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Martínez, R.

Mata, J.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

Meloni, G.

Merayo, N.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

Monroy, I. T.

Morales, F.

Morikawa, H.

T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.

Muñoz, R.

Murthy, C. S. R.

Y. V. Kiran, T. Venkatesh, and C. S. R. Murthy, “A reinforcement learning framework for path selection and wavelength selection in optical burst switched networks,” IEEE J. Select Areas Commun., vol.  25, no. 9, pp. 18–26, Dec. 2007.
[Crossref]

Musumeci, F.

S. Shahkarami, F. Musumeci, F. Cugini, and M. Tornatore, “Machine-learning-based soft-failure detection and identification in optical networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper M3A.5.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

Muthusamy, V.

E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.

Nag, A.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

Napoli, A.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Nebendahl, B.

Norvig, P.

S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed. Upper Saddle River, NJ: Prentice Hall, 2009.

Okonkwo, C.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Pandey, S.

S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
[Crossref]

Papadimitriou, G. I.

Paparrizos, J.

J. Paparrizos and L. Gravano, “k-shape: efficient and accurate clustering of time series,” SIGMOD Rec., vol.  45, no. 1, pp. 69–76, June 2016.
[Crossref]

Pederzolli, F.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Petridou, S. G.

Piels, M.

Poggiolini, P.

Pomportsis, A. S.

Potì, L.

Proietti, R.

Rafique, D.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
[Crossref]

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

D. Rafique and A. D. Ellis, “Nonlinear and ROADM induced penalties in 28 Gbaud dynamic optical mesh networks employing electronic signal processing,” Opt. Express, vol.  19, no. 18, pp. 16739–16748, Aug. 2011.
[Crossref]

D. Rafique, “Machine learning based optimal modulation format prediction for physical layer network planning,” in Int. Conf. Transparent Optical Networks, IEEE, 2018, paper Tu.A3.5.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.

D. Rafique, H. Griesser, and J. P. Elbers, “Enabling 64Gbaud coherent optical transceivers,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

D. Rafique, T. Szyrkowiec, A. Autenrieth, and J.-P. Elbers, “Analytics-driven fault discovery and diagnosis for cognitive root cause analysis,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper W4F.6.

Rahman, T.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Rottondi, C.

L. Barletta, A. Giusti, C. Rottondi, and M. Tornatore, “QoT estimation for unestablished lighpaths using machine learning,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

Ruffini, M.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

Ruiz, M.

Russell, S.

S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed. Upper Saddle River, NJ: Prentice Hall, 2009.

Samadi, P.

Y. Huang, P. B. Cho, P. Samadi, and K. Bergman, “Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Sambo, N.

Sarigiannidis, P. G.

Schlkopf, B.

O. Chapelle, B. Schlkopf, and A. Zien, Semi-Supervised Learning, 1st ed. MIT, 2010.

Shahkarami, S.

S. Shahkarami, F. Musumeci, F. Cugini, and M. Tornatore, “Machine-learning-based soft-failure detection and identification in optical networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper M3A.5.

Shariati, B.

Shikhmanter, Y.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Singh, S. K.

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

Siracusa, D.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Sköldström, P.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Slominski, A.

E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.

Spinnler, B.

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Stavdas, A.

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

Stork, D. G.

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York, NY: Wiley, 2000.

Sutton, R. S.

R. S. Sutton and A. G. Barto, Introduction to Reinforcement Learning, 1st ed. Cambridge, MA: MIT, 1998.

Szyrkowiec, T.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
[Crossref]

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

D. Rafique, T. Szyrkowiec, A. Autenrieth, and J.-P. Elbers, “Analytics-driven fault discovery and diagnosis for cognitive root cause analysis,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper W4F.6.

Tanimura, T.

T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.

Tembo, S. R.

S. R. Tembo, S. Vaton, J. L. Courant, and S. Gosselin, “A tutorial on the EM algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks,” in Int. Wireless Communications and Mobile Computing Conf. (IWCMC), Sept. 2016, pp. 369–376.

Tibshirani, R.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd ed. Springer, 2009.

Tomkos, I.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

Tornatore, M.

S. Shahkarami, F. Musumeci, F. Cugini, and M. Tornatore, “Machine-learning-based soft-failure detection and identification in optical networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper M3A.5.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

L. Barletta, A. Giusti, C. Rottondi, and M. Tornatore, “QoT estimation for unestablished lighpaths using machine learning,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

Vaton, S.

S. R. Tembo, S. Vaton, J. L. Courant, and S. Gosselin, “A tutorial on the EM algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks,” in Int. Wireless Communications and Mobile Computing Conf. (IWCMC), Sept. 2016, pp. 369–376.

Vela, A. P.

Velasco, L.

Venkatesh, T.

Y. V. Kiran, T. Venkatesh, and C. S. R. Murthy, “A reinforcement learning framework for path selection and wavelength selection in optical burst switched networks,” IEEE J. Select Areas Commun., vol.  25, no. 9, pp. 18–26, Dec. 2007.
[Crossref]

Vilalta, R.

Vukovic, M.

E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.

Vusirikala, V.

V. Vusirikala, “A decade of software defined networking at Google,” in European Conf. Optical Communications, Sept. 2018.

Watanabe, S.

T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.

Watkins, C. J. C. H.

C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol.  8, no. 3, pp. 279–292, May 1992.
[Crossref]

Wiegand, M.

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

Wittern, E.

E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.

Won, Y. J.

S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
[Crossref]

Yoo, S. J. B.

Zibar, D.

Zien, A.

O. Chapelle, B. Schlkopf, and A. Zien, Semi-Supervised Learning, 1st ed. MIT, 2010.

Annu. Math. Stat. (1)

F. E. Grubbs, “Sample criteria for testing outlying observations,” Annu. Math. Stat., vol.  21, no. 1, pp. 27–58, Mar. 1950.
[Crossref]

Found. Trends Mach. Learn. (1)

Y. Bengio, “Learning deep architectures for AI,” Found. Trends Mach. Learn., vol.  2, no. 1, pp. 1–127, Jan. 2009.
[Crossref]

IEEE Access (1)

A. Gupta and R. K. Jha, “A survey of 5G network: architecture and emerging technologies,” IEEE Access, vol.  3, pp. 1206–1232, 2015.
[Crossref]

IEEE Commun. Mag. (1)

L. Velasco, L. M. Contreras, G. Ferraris, A. Stavdas, F. Cugini, M. Wiegand, and J. P. Fernandez-Palacios, “A service-oriented hybrid access network and clouds architecture,” IEEE Commun. Mag., vol.  53, no. 4, pp. 159–165, Apr. 2015.
[Crossref]

IEEE J. Select Areas Commun. (1)

Y. V. Kiran, T. Venkatesh, and C. S. R. Murthy, “A reinforcement learning framework for path selection and wavelength selection in optical burst switched networks,” IEEE J. Select Areas Commun., vol.  25, no. 9, pp. 18–26, Dec. 2007.
[Crossref]

IEEE Photon. Technol. Lett. (1)

T. Rahman, A. Napoli, D. Rafique, B. Spinnler, M. Kuschnerov, I. Lobato, B. Clouet, M. Bohn, C. Okonkwo, and H. de Waardt, “On the mitigation of optical filtering penalties originating from ROADM cascade,” IEEE Photon. Technol. Lett., vol.  26, no. 2, pp. 154–157, Jan. 2014.
[Crossref]

Int. J. Netw. Manage. (1)

S. Pandey, M.-J. Choi, Y. J. Won, and J. W.-K. Hong, “SNMP-based enterprise IP network topology discovery,” Int. J. Netw. Manage., vol.  21, no. 3, pp. 169–184, May 2011.
[Crossref]

J. Lightwave Technol. (6)

D. Zibar, L. H. H. de Carvalho, M. Piels, A. Doberstein, J. Diniz, B. Nebendahl, C. Franciscangelis, J. Estaran, H. Haisch, N. G. Gonzalez, J. C. R. F. de Oliveira, and I. T. Monroy, “Application of machine learning techniques for amplitude and phase noise characterization,” J. Lightwave Technol., vol.  33, no. 7, pp. 1333–1343, Apr. 2015.
[Crossref]

R. Casellas, R. Martínez, R. Vilalta, and R. Muñoz, “Control, management, and orchestration of optical networks: evolution, trends, and challenges,” J. Lightwave Technol., vol.  36, no. 7, pp. 1390–1402, Apr. 2018.
[Crossref]

S. G. Petridou, P. G. Sarigiannidis, G. I. Papadimitriou, and A. S. Pomportsis, “On the use of clustering algorithms for message scheduling in WDM star networks,” J. Lightwave Technol., vol.  26, no. 17, pp. 2999–3010, Sept. 2008.
[Crossref]

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “Cognitive assurance architecture for optical network fault management,” J. Lightwave Technol., vol.  36, no. 7, pp. 1443–1450, Apr. 2018.
[Crossref]

P. Poggiolini, “The GN model of non-linear propagation in uncompensated coherent optical systems,” J. Lightwave Technol., vol.  30, no. 24, pp. 3857–3879, Dec. 2012.
[Crossref]

A. P. Vela, M. Ruiz, F. Fresi, N. Sambo, F. Cugini, G. Meloni, L. Potì, L. Velasco, and P. Castoldi, “BER degradation detection and failure identification in elastic optical networks,” J. Lightwave Technol., vol.  35, no. 21, pp. 4595–4604, Nov. 2017.
[Crossref]

J. Opt. Commun. Netw. (3)

Mach. Learn. (1)

C. J. C. H. Watkins and P. Dayan, “Q-learning,” Mach. Learn., vol.  8, no. 3, pp. 279–292, May 1992.
[Crossref]

Opt. Express (1)

Opt. Switching Netw. (1)

J. Mata, I. de Miguel, R. J. Durán, N. Merayo, S. K. Singh, A. Jukan, and M. Chamania, “Artificial intelligence (AI) methods in optical networks: a comprehensive survey,” Opt. Switching Netw., vol.  28, pp. 43–57, 2018.
[Crossref]

SIGMOD Rec. (1)

J. Paparrizos and L. Gravano, “k-shape: efficient and accurate clustering of time series,” SIGMOD Rec., vol.  45, no. 1, pp. 69–76, June 2016.
[Crossref]

Other (23)

R. S. Sutton and A. G. Barto, Introduction to Reinforcement Learning, 1st ed. Cambridge, MA: MIT, 1998.

“TensorFlow–An open source machine learning framework for everyone,” GitHub. Inc, 2018 [Online]. Available: https://www.tensorflow.org/ .

S. R. Tembo, S. Vaton, J. L. Courant, and S. Gosselin, “A tutorial on the EM algorithm for Bayesian networks: application to self-diagnosis of GPON-FTTH networks,” in Int. Wireless Communications and Mobile Computing Conf. (IWCMC), Sept. 2016, pp. 369–376.

D. Rafique, T. Szyrkowiec, A. Autenrieth, and J.-P. Elbers, “Analytics-driven fault discovery and diagnosis for cognitive root cause analysis,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper W4F.6.

Y. Huang, P. B. Cho, P. Samadi, and K. Bergman, “Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

D. Rafique, T. Szyrkowiec, H. Grießer, A. Autenrieth, and J.-P. Elbers, “TSDN-enabled network assurance: a cognitive fault detection architecture,” in 43rd European Conf. Optical Communication (ECOC), 2017.

“gRPC—An RPC library and framework,” GitHub. Inc, 2015 [Online]. Available: https://github.com/grpc/grpc .

E. Wittern, J. Laredo, M. Vukovic, V. Muthusamy, and A. Slominski, “A graph-based data model for API ecosystem insights,” in IEEE Int. Conf. Web Services, June 2014, pp. 41–48.

F. Musumeci, C. Rottondi, A. Nag, I. Macaluso, D. Zibar, M. Ruffini, and M. Tornatore, “A survey on application of machine learning techniques in optical networks,” arXiv:1803.07976, Mar. 2018.

S. Marsland, Machine Learning: An Algorithmic Perspective, CRC Press, 2011.

O. Chapelle, B. Schlkopf, and A. Zien, Semi-Supervised Learning, 1st ed. MIT, 2010.

S. Shahkarami, F. Musumeci, F. Cugini, and M. Tornatore, “Machine-learning-based soft-failure detection and identification in optical networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper M3A.5.

S. B. Kotsiantis, “Supervised machine learning: a review of classification techniques,” in Emerging Artificial Intelligence Applications in Computer Engineering—Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies, IOS, 2007, pp. 3–24.

V. Vusirikala, “A decade of software defined networking at Google,” in European Conf. Optical Communications, Sept. 2018.

D. Rafique, H. Griesser, and J. P. Elbers, “Enabling 64Gbaud coherent optical transceivers,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

V. Lopez, J. M. Gran, R. Jimenez, J. P. Fernandez-Palacios, D. Siracusa, F. Pederzolli, O. Gerstel, Y. Shikhmanter, J. Mårtensson, P. Sköldström, T. Szyrkowiec, M. Chamania, A. Autenrieth, I. Tomkos, and D. Klonidis, “The role of SDN in application centric IP and optical networks,” in European Conf. Networks and Communications (EuCNC), June 2016, pp. 138–142.

M. Ruiz and L. Velasco, Provisioning, Recovery, and In Operation Planning in Elastic Optical Networks, Wiley, 2017.

S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 3rd ed. Upper Saddle River, NJ: Prentice Hall, 2009.

R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification, 2nd ed. New York, NY: Wiley, 2000.

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference and Prediction, 2nd ed. Springer, 2009.

L. Barletta, A. Giusti, C. Rottondi, and M. Tornatore, “QoT estimation for unestablished lighpaths using machine learning,” in Optical Fiber Communications Conf. and Exhibition (OFC), Mar. 2017, pp. 1–3.

T. Tanimura, T. Hoshida, T. Kato, S. Watanabe, and H. Morikawa, “Data analytics based optical performance monitoring technique for optical transport networks,” in Optical Fiber Communication Conf., Optical Society of America, 2018, paper Tu3E.3.

D. Rafique, “Machine learning based optimal modulation format prediction for physical layer network planning,” in Int. Conf. Transparent Optical Networks, IEEE, 2018, paper Tu.A3.5.

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.


Figures (23)

Fig. 1.
Fig. 1. Heterogeneous optical network architecture.
Fig. 2.
Fig. 2. Machine learning model construction and test workflow.
Fig. 3.
Fig. 3. ML families. The first box in each column identifies the main characterization of the ML approach; the second box identifies examples of algorithms used in the approach; and the third box indicates examples of applications that can take advantage of the approach.
Fig. 4.
Fig. 4. Illustrative example of a dual-layer ANN architecture.
Fig. 5.
Fig. 5. Underfitting versus overfitting.
Fig. 6.
Fig. 6. k -fold cross-validation.
Fig. 7.
Fig. 7. ROC- and AUC-based classifier evaluation. The dotted and dashed lines are examples of typical ROC curves; the classifier corresponding to the dashed line provides better performance.
Fig. 8.
Fig. 8. Model-driven telemetry stack. REST, representational state transfer; RHU, remote hub unit; VNF, virtual network function.
Fig. 9.
Fig. 9. Data storage and representation workflow and technologies.
Fig. 10.
Fig. 10. Self-driven networking architecture.
Fig. 11.
Fig. 11. Adaptive model update based on changing data profile, as opposed to fixed duration periodic updates. (a) Normal distribution of optical power levels. (b) Abnormal distribution of optical power levels.
Fig. 12.
Fig. 12. Fault management functional hierarchy.
Fig. 13.
Fig. 13. SDN-integrated fault discovery (detection) and diagnosis. (a) System-level FDD. (b) Node-level FDD.
Fig. 14.
Fig. 14. (a) Localized fault discovery at the node. (b) Local feature similarity analysis for root cause analysis.
Fig. 15.
Fig. 15. (a)–(c) Reactive and proactive adaptation. Numbers in the inset represent link capacity in gigabits per second (Gb/s). (d) Maximum prediction error versus days of monitoring.
Fig. 16.
Fig. 16. (a) and (b) Prediction of min/max/avg for two different traffic profiles, and (c) ANN adaptation to smooth evolutionary bit rate.
Fig. 17.
Fig. 17. Maximum used transponders versus load.
Fig. 18.
Fig. 18. Network setup and ML input and output parameters.
Fig. 19.
Fig. 19. (a) Classifiers’ performance. (b) Training time.
Fig. 20.
Fig. 20. Example of optical spectrum and signal features.
Fig. 21.
Fig. 21. Example of filter failures considered in this paper: (a) FS and (b) FT.
Fig. 22.
Fig. 22. Workflow for filter failure detection and identification.
Fig. 23.
Fig. 23. Accuracy of the proposed method for (a) FS and (b) FT identification.

Tables (5)

Tables Icon

Algorithm 2 Q-Learning

Tables Icon

TABLE I Confusion Matrix for a Binary Classifier

Tables Icon

TABLE II Examples of Optical Network Data Sources

Tables Icon

TABLE III Legacy Versus Model-Driven Network Telemetry