AI-Based Modeling and Monitoring Techniques for Future Intelligent Elastic Optical Networks
Source abstract
Abstract
With the development of 5G technology, high definition video and internet of things, the capacity demand for optical networks has been increasing dramatically. To fulfill the capacity demand, low-margin optical network is attracting attentions. Therefore, planning tools with higher accuracy are needed and accurate models for quality of transmission (QoT) and impairments are the key elements to achieve this. Moreover, since the margin is low, maintaining the reliability of the optical network is also essential and optical performance monitoring (OPM) is desired. With OPM, controllers can adapt the configuration of the physical layer and detect anomalies. However, considering the heterogeneity of the modern optical network, it is difficult to build such accurate modeling and monitoring tools using traditional analytical methods. Fortunately, data-driven artificial intelligence (AI) provides a promising path. In this paper, we firstly discuss the requirements for adopting AI approaches in optical networks. Then, we review various recent progress of AI-based QoT/impairments modeling and monitoring schemes. We categorize these proposed methods by their functions and summarize advantages and challenges of adopting AI methods for these tasks. We discuss the problems remained for deploying AI-based methods to a practical system and present some possible directions for future investigation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Optical Network Technologies · Advanced Optical Network Technologies · Advanced Photonic Communication Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Shanghai Institute for Advanced Communication and Data Science, State Key Laboratory of Advanced Optical Communication Systems and Networks, Department of Electronic Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Funding
National Natural Science Foundation of China · Shanghai Rising-Star Program · National Key R&D Program of China
References (75)
Show source-provided references
1. Optical networking: Past, present, and future10.1109/JLT.2008.923609 ↗
2. Optical performance monitoring: A review of current and future technologies10.1109/JLT.2015.2480798 ↗
3. Design of low-margin optical networks10.1364/JOCN.9.0000A9 ↗
4. Machine-learning method for quality of transmission prediction of unestablished lightpaths10.1364/JOCN.10.00A286 ↗
5. Application of machine learning in fiber nonlinearity modeling and monitoring for elastic optical networks10.1109/JLT.2019.2910143 ↗
6. Optimization of the split-step fourier method in modeling optical-fiber communications systems10.1109/JLT.2003.808628 ↗
7. The GN model of non-linear propagation in uncompensated coherent optical systems10.1109/JLT.2012.2217729 ↗
8. Cheeseman, P., and Gevarter, W. (1986, January 6–8). Introduction to artificial intelligence. Proceedings of the 24th Aerospace Sciences Meeting, American Institute of Aeronautics and Astronautics, Reno, NV, USA.10.2514/6.1986-163 ↗
9. Optical filtering penalty estimation using artificial neural network in elastic optical networks with cascaded reconfigurable optical add–drop multiplexers10.1117/1.OE.58.7.076105 ↗
10. (Manos) Accurate quality of transmission estimation with machine learning10.1364/JOCN.11.000140 ↗
11. Introduction to multi-layer feed-forward neural networks10.1016/S0169-7439(97)00061-0 ↗
12. Lun, H., Zhuge, Q., Fu, M., Wu, Y., Liu, Q., Cai, M., Zeng, X., and Hu, W. (2019, January 22–26). Soft failure identification in optical networks based on convolutional neural network. Proceedings of the 2019 European Conference on Optical Communication, Dublin, Ireland.
13. Tanimura, T., Hoshida, T., Kato, T., Watanabe, S., and Morikawa, H. (2018, January 11–15). Data-analytics-based optical performance monitoring technique for optical transport networks. Proceedings of the Optical Fiber Communication Conference, San Diego, CA, USA.10.1364/OFC.2018.Tu3E.3 ↗
14. Optical performance monitoring using artificial neural networks trained with empirical moments of asynchronously sampled signal amplitudes10.1109/LPT.2012.2190762 ↗
15. Learning from the optical spectrum: Failure detection and identification10.1109/JLT.2018.2859199 ↗
16. An overview on application of machine learning techniques in optical networks10.1109/COMST.2018.2880039 ↗
17. An optical communication’s perspective on machine learning and Its applications10.1109/JLT.2019.2897313 ↗
18. Machine learning for network automation: Overview, architecture, and applications [Invited Tutorial]10.1364/JOCN.10.00D126 ↗
19. Artificial intelligence (AI) methods in optical networks: A comprehensive survey10.1016/j.osn.2017.12.006 ↗
20. Joint defragmentation of optical spectrum and IT resources in elastic optical datacenter interconnections10.1364/JOCN.7.000314 ↗
21. Marginless operation of optical networks10.1109/JLT.2018.2881840 ↗
22. Software-defined optical networks technology and infrastructure: Enabling software-defined optical network operations [Invited]10.1364/JOCN.5.00A274 ↗
23. Performance analysis of a data-driven quality-of-transmission decision approach on a dynamic multicast-capable metro optical network10.1364/JOCN.9.000098 ↗
24. Politi, C., Anagnostopoulos, V., Matrakidis, C., and Stavdas, A. (2006, January 5–10). Physical layer impairment aware routing algorithms based on analytically calculated Q-factor. Proceedings of the 2006 Optical Fiber Communication Conference and the National Fiber Optic Engineers Conference, Anaheim, CA, USA.10.1109/OFC.2006.215971 ↗
25. Multicast routing algorithms based on Q-factor physical-layer constraints in metro networks10.1109/LPT.2008.2011750 ↗
26. Learning life cycle to speed up autonomic optical transmission and networking adoption10.1364/JOCN.11.000226 ↗
27. Fast analytical evaluation of fiber nonlinear noise variance in mesh optical networks10.1364/JOCN.9.000C88 ↗
28. Network planning strategies for next-generation flexible optical networks [Invited]10.1364/JOCN.7.00A511 ↗
29. Comparison of split-step Fourier schemes for simulating fiber optic communication systems
30. Higher-order split-step Fourier schemes for the generalized nonlinear Schrödinger equation10.1016/j.matcom.2004.08.002 ↗
31. On the accuracy of split-step Fourier simulations for wideband nonlinear optical communications10.1109/JLT.2018.2877384 ↗
32. Murty, M.N., and Devi, V.S. (2015). Introduction to Pattern Recognition and Machine Learning, Co-Published with Indian Institute of Science (IISc).
33. Mo, W., Huang, Y.-K., Zhang, S., Ip, E., Kilper, D.C., Aono, Y., and Tajima, T. (2018, January 11–15). ANN-based transfer learning for QoT prediction in real-time mixed line-rate systems. Proceedings of the Optical Fiber Communication Conference, San Diego, CA, USA.10.1364/OFC.2018.W4F.3 ↗
34. Zhu, S., Gutterman, C.L., Mo, W., Li, Y., Zussman, G., and Kilper, D.C. (2018, January 23–27). Machine learning based prediction of Erbium-Doped fiber WDM Line amplifier gain spectra. Proceedings of the 2018 European Conference on Optical Communication (ECOC), Rome, Italy.10.1109/ECOC.2018.8535323 ↗
35. You, Y., Jiang, Z., and Janz, C. (2018, January 23–27). Machine learning-based EDFA gain model. Proceedings of the 2018 European Conference on Optical Communication (ECOC), Rome, Italy.10.1109/ECOC.2018.8535397 ↗
36. EDFA wavelength dependent gain spectrum measurement using weak optical probe sampling10.1109/LPT.2017.2779746 ↗
37. Yan, S., Khan, F.N., Mavromatis, A., Gkounis, D., Fan, Q., Ntavou, F., Nikolovgenis, K., Meng, F., Salas, E.H., and Guo, C. (2017, January 17–21). Field trial of machine-learning-assisted and SDN-based optical network planning with network-scale monitoring database. Proceedings of the 2017 European Conference on Optical Communication (ECOC), Gothenburg, Sweden.10.1109/ECOC.2017.8346091 ↗
38. Machine learning models for estimating quality of transmission in DWDM networks10.1364/JOCN.10.000D84 ↗
39. Wang, J., and Luo, S. (2006, January 13–16). Exploiting ensemble method in semi-supervised learning. Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, Dalian, China.10.1109/ICMLC.2006.258568 ↗
40. A note on the Theil-Sen regression estimator when the regressor Is random and the error term is heteroscedastic10.1002/(SICI)1521-4036(199807)40:3<261::AID-BIMJ261>3.0.CO;2-V ↗
41. Wong, S.C., Gatt, A., Stamatescu, V., and McDonnell, M.D. (2016). Understanding data augmentation for classification: When to warp?. arXiv.10.1109/DICTA.2016.7797091 ↗
42. The art of data augmentation10.1198/10618600152418584 ↗
43. Michie, D., Spiegelhalter, D.J., and Taylor, C.C. (1994). Machine Learning, Neural and Statistical Classification, Prentice Hall.
44. Using machine learning in communication networks [Invited]10.1364/JOCN.10.00D100 ↗
45. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2014). Caffe: Convolutional architecture for fast feature embedding. arXiv.10.1145/2647868.2654889 ↗
46. Panayiotou, T., Savva, G., Shariati, B., Tomkos, I., and Ellinas, G. (2019, January 3–7). Machine learning for QoT estimation of unseen optical network states. Proceedings of the Optical Fiber Communication Conference (OFC) 2019, San Diego, CA, USA.10.1364/OFC.2019.Tu2E.2 ↗
47. Cognitive dynamic optical networks [Invited]10.1364/JOCN.5.00A107 ↗
48. A cognitive quality of transmission estimator for core optical networks10.1109/JLT.2013.2240257 ↗
49. Lightpath establishment assisted by offline QoT estimation in transparent optical networks10.1364/JOCN.2.000928 ↗
50. Meng, F., Yan, S., Nikolovgenis, K., Ou, Y., Wang, R., Bi, Y., Hugues-Salas, E., Nejabati, R., and Simeonidou, D. (2018, January 11–15). Field trial of gaussian process learning of function-agnostic channel performance under uncertainty. Proceedings of the Optical Fiber Communication Conference, San Diego, CA, USA.10.1364/OFC.2018.W4F.5 ↗
51. Learning process for reducing uncertainties on network parameters and design margins10.1364/JOCN.10.00A298 ↗
52. Transfer learning assisted deep neural network for OSNR estimation10.1364/OE.27.019398 ↗
53. A simple and effective closed-form GN model correction formula accounting for signal non-gaussian distribution10.1109/JLT.2014.2387891 ↗
54. Spectral hole burning in erbium-doped fiber amplifiers10.1109/JLT.2003.810084 ↗
55. Characterization of real-time PMD and chromatic dispersion monitoring in a High-PMD 46-Gb/s transmission system10.1109/LPT.2008.2006189 ↗
56. Geyer, J.C., Fludger, C.R.S., Duthel, T., Schulien, C., and Schmauss, B. (2009, January 20–22). Optical performance monitoring using a 43Gb/s realtime coherent receiver. Proceedings of the 2009 IEEE/LEOS Summer Topical Meeting, Newport Beach, CA, USA.10.1109/LEOSST.2009.5226223 ↗
57. Tanimura, T., Hoshida, T., Rasmussen, J.C., Suzuki, M., and Morikawa, H. (2016, January 3–7). OSNR monitoring by deep neural networks trained with asynchronously sampled data. Proceedings of the 2016 21st OptoElectronics and Communications Conference (OECC) Held Jointly with 2016 International Conference on Photonics in Switching (PS), Niigata, Japan.
58. Intelligent constellation diagram analyzer using convolutional neural network-based deep learning10.1364/OE.25.017150 ↗
59. Convolutional neural network-based optical performance monitoring for optical transport networks10.1364/JOCN.11.000A52 ↗
60. Simultaneous optical performance monitoring and modulation format/bit-rate identification using principal component analysis10.1364/JOCN.6.000441 ↗
61. Khan, F.N., Yu, Y., Tan, M.C., Yu, C., Lau, A.P.T., and Lu, C. (2015, January 19–23). Simultaneous OSNR monitoring and modulation format identification using asynchronous single channel sampling. Proceedings of the Asia Communications and Photonics Conference 2015, Hong Kong, China.10.1364/ACPC.2015.AS4F.6 ↗
62. Joint OSNR monitoring and modulation format identification in digital coherent receivers using deep neural networks10.1364/OE.25.017767 ↗
63. Multi Impairment monitoring for optical networks10.1109/JLT.2009.2025052 ↗
64. Long short-term memory neural network (LSTM-NN) enabled accurate optical signal-to-noise ratio (OSNR) monitoring10.1109/JLT.2019.2904263 ↗
65. OSNR and nonlinear noise power estimation for optical fiber communication systems using LSTM based deep learning technique10.1364/OE.26.021346 ↗
66. Automatic identification of impairments using support vector machine pattern classification on eye diagrams10.1109/LPT.2006.886146 ↗
67. Kashi, A.S., Zhuge, Q., Cartledge, J., Borowiec, A., Charlton, D., Laperle, C., and O’Sullivan, M. (2017, January 10–13). Artificial neural networks for fiber nonlinear noise estimation. Proceedings of the Asia Communications and Photonics Conference, Guangzhou, China.10.1364/ACPC.2017.Su1B.6 ↗
68. Vaquero Caballero, F.J., Ives, D., Zhuge, Q., O’Sullivan, M., and Savory, S.J. (2018, January 11–15). Joint estimation of linear and non-linear signal-to-noise ratio based on neural networks. Proceedings of the Optical Fiber Communication Conference, San Diego, CA, USA.10.1364/OFC.2018.M2F.4 ↗
69. Zhang, K., Fan, Y., Ye, T., Tao, Z., Oda, S., Tanimura, T., Akiyama, Y., and Hoshida, T. (2019, January 3–7). Fiber nonlinear noise-to-signal ratio estimation by machine learning. Proceedings of the Optical Fiber Communication Conference (OFC) 2019, San Diego, CA, USA.10.1364/OFC.2019.Th2A.45 ↗
70. BER degradation detection and failure identification in elastic optical networks10.1109/JLT.2017.2747223 ↗
71. Shahkarami, S., Musumeci, F., Cugini, F., and Tornatore, M. (2018, January 11–15). Machine-learning-based soft-failure detection and identification in optical networks. Proceedings of the Optical Fiber Communication Conference, San Diego, CA, USA.10.1364/OFC.2018.M3A.5 ↗
72. Varughese, S., Lippiatt, D., Richter, T., Tibuleac, S., and Ralph, S.E. (2019, January 3–7). Identification of soft failures in optical links using low complexity anomaly detection. Proceedings of the Optical Fiber Communication Conference (OFC) 2019, San Diego, CA, USA.10.1364/OFC.2019.W2A.46 ↗
73. A tutorial on machine learning for failure management in optical networks10.1109/JLT.2019.2922586 ↗
74. Making machine learning models interpretable
75. Boitier, F., and Layec, P. (2018, January 1–5). Automated optical networks with monitoring and machine learning. Proceedings of the 2018 20th International Conference on Transparent Optical Networks (ICTON), Bucharest, Romania.10.1109/ICTON.2018.8473802 ↗