logo

SCIENCE CHINA Information Sciences, Volume 63 , Issue 6 : 160302(2020) https://doi.org/10.1007/s11432-020-2874-y

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

More info
  • ReceivedFeb 27, 2020
  • AcceptedApr 13, 2020
  • PublishedMay 12, 2020

Abstract

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


Acknowledgment

This work was supported by National Natural Science Foundation of China (Grant No. 61801291), Shanghai Rising-Star Program (Grant No. 19QA1404600), and National Key RD Program of China (Grant No. 2018YFB- 1801200).


References

[1] Gupta A, Jha R K. A Survey of 5G Network: Architecture and Emerging Technologies. IEEE Access, 2015, 3: 1206-1232 CrossRef Google Scholar

[2] Gerstel O, Jinno M, Lord A, et al. Elastic optical networking: a new dawn for the optical layer? IEEE Communications Magazine, 2012, 50: s12-s20. Google Scholar

[3] Pointurier Y. Design of Low-Margin Optical Networks. J Opt Commun Netw, 2017, 9: A9 CrossRef Google Scholar

[4] Perin J K, Roberts I, Kahn J M. Improving the capacity of terrestrial and submarine systems via channel power optimization. In: Proceedings of International Conference on Transparent Optical Networks, 2018. 1--4. Google Scholar

[5] Martin I, Hernandez J A, Troia S, et al. Is machine learning suitable for solving RWA problems in optical networks? In: Proceedings of European Conference on Optical Communication, 2018. 1--3. Google Scholar

[6] Musumeci F, Rottondi C, Corani G. A Tutorial on Machine Learning for Failure Management in Optical Networks. J Lightwave Technol, 2019, 37: 4125-4139 CrossRef ADS Google Scholar

[7] Rafique D, Velasco L. Machine Learning for Network Automation: Overview, Architecture, and Applications [Invited Tutorial]. J Opt Commun Netw, 2018, 10: D126 CrossRef Google Scholar

[8] C?té D. Using Machine Learning in Communication Networks [Invited]. J Opt Commun Netw, 2018, 10: D100 CrossRef Google Scholar

[9] Zhao Y, Yan B, Liu D. SOON: self-optimizing optical networks with machine learning. Opt Express, 2018, 26: 28713 CrossRef PubMed ADS Google Scholar

[10] Xie J F, Yu F R, Huang T, et al. A survey of machine learning techniques applied to software defined networking (SDN): research issues and challenges. IEEE Communications Surveys & Tutorials, 2019, 21: 393-430. Google Scholar

[11] Musumeci F, Rottondi C, Nag A, et al. An overview on application of machine learning techniques in optical networks. IEEE Communications Surveys & Tutorials, 2019, 21: 1383-1408. Google Scholar

[12] Khan F N, Fan Q, Lu C. An Optical Communication's Perspective on Machine Learning and Its Applications. J Lightwave Technol, 2019, 37: 493-516 CrossRef ADS Google Scholar

[13] Kaelbling L P, Littman M L, Moore A W. An introduction to reinforcement learning. IEEE Press, 1995,10: 90-127. Google Scholar

[14] Boertjes D W, Reimer M, C?té D. Practical considerations for near-zero margin network design and deployment [Invited]. J Opt Commun Netw, 2019, 11: C25 CrossRef Google Scholar

[15] Kashi A S, Zhuge Q, Cartledge J C. Nonlinear Signal-to-Noise Ratio Estimation in Coherent Optical Fiber Transmission Systems Using Artificial Neural Networks. J Lightwave Technol, 2018, 36: 5424-5431 CrossRef ADS Google Scholar

[16] Li B J, Zhu Z Q. DeepCoop: leveraging cooperative DRL agents to achieve scalable network automation for multi-domain SD-EONs. In: Proceedings of Optical Fiber Communication Conference, 2020. TH2A.29. Google Scholar

[17] Auge J L. Can we use flexible transponders to reduce margins? In: Proceedings of Optical Fiber Communication Conference, 2013. OTu2A.1. Google Scholar

[18] Poggiolini P, Bosco G, Carena A. The GN-Model of Fiber Non-Linear Propagation and its Applications. J Lightwave Technol, 2014, 32: 694-721 CrossRef ADS Google Scholar

[19] Pesic J, Lonardi M, Rossi N, et al. How uncertainty on the fiber span lengths influences qot estimation using machine learning in wdm networks. In: Proceedings of Optical Fiber Communication Conference, 2020. Th3D.5. Google Scholar

[20] Sartzetakis I, Christodoulopoulos K K, Varvarigos E M. Accurate Quality of Transmission Estimation With Machine Learning. J Opt Commun Netw, 2019, 11: 140 CrossRef Google Scholar

[21] Meng F, Yan S, Nikolovgenis K, et al. Field trial of Gaussian process learning of function-agnostic channel performance under uncertainty. In: Proceedings of Optical Fiber Communication Conference, 2018. W4F.5. Google Scholar

[22] Yan S Y, Khan F N, Mavromatis A, et al. Field trial of machine-learning-assisted and SDN-based optical network management. In: Proceedings of Optical Fiber Communication Conference, 2019. M2E.1. Google Scholar

[23] Mo W Y, Huang Y K, Zhang S L, et al. ANN-based transfer learning for QoT prediction in real-time mixed line-rate systems. In: Proceedings of Optical Fiber Communication Conference, 2018. W4F.3. Google Scholar

[24] Rottondi C, Barletta L, Giusti A. Machine-Learning Method for Quality of Transmission Prediction of Unestablished Lightpaths. J Opt Commun Netw, 2018, 10: A286 CrossRef Google Scholar

[25] Panayiotou T, Savva G, Shariati B, et al. Machine learning for QoT estimation of unseen optical network states. In: Proceedings of Optical Fiber Communication Conference, 2019. Tu2E.2. Google Scholar

[26] Morais R M, Pedro J. Machine Learning Models for Estimating Quality of Transmission in DWDM Networks. J Opt Commun Netw, 2018, 10: D84 CrossRef Google Scholar

[27] Azzimonti D, Rottondi C, Giusti A, et al. Active vs transfer learning approaches for QoT estimation with small training datasets. In: Proceedings of Optical Fiber Communication Conference, 2020. M4E.1. Google Scholar

[28] Liu C Y, Chen X L, Proietti R, et al. Evol-tl: evolutionary transfer learning for QoT estimation in multi-domain networks. In: Proceedings of Optical Fiber Communication Conference, 2020. Th3D.1. Google Scholar

[29] Zhuge Q, Zeng X, Lun H. Application of Machine Learning in Fiber Nonlinearity Modeling and Monitoring for Elastic Optical Networks. J Lightwave Technol, 2019, 37: 3055-3063 CrossRef ADS arXiv Google Scholar

[30] Tremblay C, Allogba S, Aladin S. Quality of transmission estimation and performance prediction of lightpaths using machine learning. In: Proceedings of European Conference on Optical Communication, 2019. 1--3. Google Scholar

[31] Seve E, Pesic J, Delezoide C. Learning Process for Reducing Uncertainties on Network Parameters and Design Margins. J Opt Commun Netw, 2018, 10: A298 CrossRef Google Scholar

[32] Bouda M, Oda S, Vassilieva O. Accurate Prediction of Quality of Transmission Based on a Dynamically Configurable Optical Impairment Model. J Opt Commun Netw, 2018, 10: A102 CrossRef Google Scholar

[33] Mahajan A, Christodoulopoulos K, Martinez R, et al. Machine learning assisted EDFA gain ripple modelling for accurate QoT estimation. In: Proceedings of European Conference on Optical Communication, 2019. 1--4. Google Scholar

[34] D'Amico A, Straullu S, Nespola A, et al. Machine-learning aided OSNR prediction in optical line systems. In: Proceedings of European Conference on Optical Communication, 2019. 1--4. Google Scholar

[35] Liu X M, Lun H Z, Fu M F, et al. A three-stage training framework for customizing link models for optical networks. In: Proceedings of Optical Fiber Communication Conference, 2020. Th3D.6. Google Scholar

[36] Zefreh M S, Asselin S. Capacity enhancement in optical networks using margin extraction. In: Proceedings of Optical Fiber Communications Conference, 2018. W4A.3. Google Scholar

[37] Delezoide C, Christodoulopoulos K, Kretsis A. Marginless Operation of Optical Networks. J Lightwave Technol, 2019, 37: 1698-1705 CrossRef ADS Google Scholar

[38] Pesic J, Rossi N, Zami T. Impact of Margins Evolution Along Ageing in Elastic Optical Networks. J Lightwave Technol, 2019, 37: 4081-4089 CrossRef ADS Google Scholar

[39] Soumplis P, Christodoulopoulos K, Quagliotti M. Multi-Period Planning With Actual Physical and Traffic Conditions. J Opt Commun Netw, 2018, 10: A144 CrossRef Google Scholar

[40] Roberts I, Kahn J M, Boertjes D. Convex Channel Power Optimization in Nonlinear WDM Systems Using Gaussian Noise Model. J Lightwave Technol, 2016, 34: 3212-3222 CrossRef ADS Google Scholar

[41] Roberts I, Kahn J M, Harley J. Channel Power Optimization of WDM Systems Following Gaussian Noise Nonlinearity Model in Presence of Stimulated Raman Scattering. J Lightwave Technol, 2017, 35: 5237-5249 CrossRef ADS Google Scholar

[42] Roberts I, Kahn J M. Efficient Discrete Rate Assignment and Power Optimization in Optical Communication Systems Following the Gaussian Noise Model. J Lightwave Technol, 2017, 35: 4425-4437 CrossRef ADS Google Scholar

[43] Roberts I, Kahn J M. Measurement-Based Optimization of Channel Powers With Non-Gaussian Nonlinear Interference Noise. J Lightwave Technol, 2018, 36: 2746-2756 CrossRef ADS Google Scholar

[44] Lonardi M, Ramantanis P, Jennevé P, et al. Optical nonlinearity monitoring and launched power optimization by artificial neural networks. In: Proceedings of European Conference on Optical Communication, 2019. 1--4. Google Scholar

[45] Huang Y S, Samoud W, Gutterman C L, et al. A machine learning approach for dynamic optical channel add/drop strategies that minimize EDFA power excursions. In: Proceedings of European Conference on Optical Communication, 2016. 1--3. Google Scholar

[46] Ahsan A S, Browning C, Wang M S. Excursion-Free Dynamic Wavelength Switching in Amplified Optical Networks. J Opt Commun Netw, 2015, 7: 898-905 CrossRef Google Scholar

[47] Lin P J. Reducing optical power variation in amplified optical network. In: Proceedings of International Conference on Communication Technology Proceedings, 2003. 42--47. Google Scholar

[48] Zhu S X, Gutterman C L, Mo W Y, et al. Machine learning based prediction of erbium-doped fiber WDM line amplifier gain spectra. In: Proceedings of European Conference on Optical Communication, 2018. 1--3. Google Scholar

[49] You Y R, Jiang Z P, Janz C. Machine learning-based EDFA gain model. In: Proceedings of European Conference on Optical Communication, 2018. 1--3. Google Scholar

[50] Huang Y, Gutterman C L, Samadi P. Dynamic mitigation of EDFA power excursions with machine learning. Opt Express, 2017, 25: 2245 CrossRef PubMed ADS Google Scholar

[51] Freire M, Mansfeld S, Amar D, et al. Predicting optical power excursions in erbium doped fiber amplifiers using neural networks. In: Proceedings of Asia Communications and Photonics Conference, 2018. 1--3. Google Scholar

[52] Gutterman C L, Mo W Y, Zhu S X, et al. Neural network based wavelength assignment in optical switching. In: Proceedings of the Workshop on Big Data Analytics and Machine Learning for Data Communication Networks, 2017. 37--42. Google Scholar

[53] Delezoide C, Christodoulopoulos K, Kretsis A, et al. Pre-emptive detection and localization of failures towards marginless operations of optical networks. In: Proceedings of International Conference on Transparent Optical Networks, 2018. 1--4. Google Scholar

[54] Ba S, Chatterjee B C, Okamoto S. Route Partitioning Scheme for Elastic Optical Networks With Hitless Defragmentation. J Opt Commun Netw, 2016, 8: 356-370 CrossRef Google Scholar

[55] Huang Y S, Cho P B, Samadi P, et al. Dynamic power pre-adjustments with machine learning that mitigate EDFA excursions during defragmentation. In: Proceedings of Optical Fiber Communication Conference, 2017. Th1J.2. Google Scholar

[56] Huang Y, Cho P B, Samadi P. Power Excursion Mitigation for Flexgrid Defragmentation With Machine Learning. J Opt Commun Netw, 2018, 10: A69 CrossRef Google Scholar

[57] Christodoulopoulos K, Tomkos I, Varvarigos E A. Elastic Bandwidth Allocation in Flexible OFDM-Based Optical Networks. J Lightwave Technol, 2011, 29: 1354-1366 CrossRef ADS Google Scholar

[58] Wu J, Ning Z, Guo L. Energy-Efficient Survivable Grooming in Software-Defined Elastic Optical Networks. IEEE Access, 2017, : 1-1 CrossRef Google Scholar

[59] Wang Y, Cao X J, Pan Y. A study of the routing and spectrum allocation in spectrum-sliced elastic optical path networks. In: Proceedings of IEEE INFOCOM, 2011. 1503--1511. Google Scholar

[60] Panayiotou T, Manousakis K, Chatzis S P. A Data-Driven Bandwidth Allocation Framework With QoS Considerations for EONs. J Lightwave Technol, 2019, 37: 1853-1864 CrossRef ADS Google Scholar

[61] Chen X L, Proietti R, Yoo S J B. Building autonomic elastic optical networks with deep reinforcement learning. IEEE Communications Magazine, 2019, 57: 20-26. Google Scholar

[62] Troia S, Rodriguez A, Martin I, et al. Machine-learning-assisted routing in SDN-based optical networks. In: Proceedings of European Conference on Optical Communication, 2018. 1--3. Google Scholar

[63] Yan B Y, Zhao Y L, Li Y J, et al. Actor-critic-based resource allocation for multi-modal optical networks. In: Proceedings of IEEE Globecom Workshops, 2018. 1--6. Google Scholar

[64] Shiraki R, Mori Y, Hasegawa H, et al. Dynamic control of transparent optical networks with adaptive state-value assessment enabled by reinforcement learning. In: Proceedings of International Conference on Transparent Optical Networks, 2019. 1--4. Google Scholar

[65] Luo X, Shi C, Chen X, et al. Comprehensive performance study of elastic optical networks for distributed datacenter with survivability. In: Proceedings of Optical Fiber Communication Conference, 2019. Th2A.23. Google Scholar

[66] Shiraki R, Mori Y, Hasegawa H, et al. Dynamically controlled flexible-grid networks based on semi-flexible spectrum assignment and network-state-value evaluation. In: Proceedings of Optical Fiber Communication Conference, 2020. M1B.4. Google Scholar

[67] Luong N C, Hoang D T, Gong S M, et al. Applications of deep reinforcement learning in communications and networking: a survey. IEEE Communications Surveys & Tutorials, 2019, 21: 3133-3174. Google Scholar

[68] Luo X, Shi C, Wang L. Leveraging double-agent-based deep reinforcement learning to global optimization of elastic optical networks with enhanced survivability. Opt Express, 2019, 27: 7896 CrossRef PubMed ADS Google Scholar

[69] Chen X L, Proietti R, Liu C Y, et al. Exploiting multi-task learning to achieve effective transfer deep reinforcement learning in elastic optical networks. In: Proceedings of Optical Fiber Communication Conference, 2020. M1B.3. Google Scholar

[70] Chen X, Li B, Proietti R. DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks. J Lightwave Technol, 2019, 37: 4155-4163 CrossRef ADS arXiv Google Scholar

[71] Suárez-V J, Mestres A, Yu J L, et al. Feature engineering for deep reinforcement learning based routing. In: Proceedings of IEEE International Conference on Communications, 2019. 1--6. Google Scholar

[72] Suárez-Varela J, Mestres A, Yu J. Routing in optical transport networks with deep reinforcement learning. J Opt Commun Netw, 2019, 11: 547 CrossRef Google Scholar

[73] Suárez-V J, Mestres A, Yu J L, et al. Routing based on deep reinforcement learning in optical transport networks. In: Proceedings of Optical Fiber Communication Conference, 2019. M2A.6. Google Scholar

[74] Almasan P, Suárez-V J, Badia-S A, et al. Deep reinforcement learning meets graph neural networks: an optical network routing use case. 2019,. arXiv Google Scholar

[75] Varughese S, Lippiatt D, Richter T, et al. Identification of soft failures in optical links using low complexity anomaly detection. In: Proceedings of Optical Fiber Communication Conference, 2019. W2A.46. Google Scholar

[76] Shu L, Yu Z M, Wan Z Q, et al. Low-complexity dual-stage soft failure detection by exploiting digital spectrum information. In: Proceedings of European Conference on Optical Communication, 2019. 1--4. Google Scholar

[77] Chen X, Li B, Proietti R. Self-Taught Anomaly Detection With Hybrid Unsupervised/Supervised Machine Learning in Optical Networks. J Lightwave Technol, 2019, 37: 1742-1749 CrossRef ADS Google Scholar

[78] Vela A P, Shariati B, Ruiz M. Soft Failure Localization During Commissioning Testing and Lightpath Operation. J Opt Commun Netw, 2018, 10: A27 CrossRef Google Scholar

[79] Shahkarami S, Musumeci F, Cugini F, et al. Machine-learning-based soft-failure detection and identification in optical networks. In: Proceedings of Optical Fiber Communication Conference, 2018. M3A.5. Google Scholar

[80] Lun H Z, Zhuge Q B, Fu M F, et al. Soft failure identification in optical networks based on convolutional neural network. In: Proceedings of European Conference on Optical Communication, 2019. 1-3. Google Scholar

[81] Varughese S, Lippiatt D, Richter T, et al. Low complexity soft failure detection and identification in optical links using adaptive filter coefficients. In: Proceedings of Optical Fiber Communication Conference, 2020. M2J.4. Google Scholar

[82] Ruiz M, Fresi F, Vela A, et al. Service-triggered failure identification/localization through monitoring of multiple parameters. In: Proceedings of European Conference on Optical Communication, 2016. 1--3. Google Scholar

[83] Zhang C Y, Wang D S, Song C, et al. Interpretable learning algorithm based on XGboost for fault prediction in optical network. In: Proceedings of Optical Fiber Communication Conference, 2020. Th1F.3. Google Scholar

[84] Panayiotou T, Chatzis S P, Ellinas G. Leveraging Statistical Machine Learning to Address Failure Localization in Optical Networks. J Opt Commun Netw, 2018, 10: 162 CrossRef Google Scholar

[85] Christodoulopoulos K, Sambo N, Varvarigos E. Exploiting network Kriging for fault localization. In: Proceedings of Optical Fiber Communication Conference, 2016. W1B.5. Google Scholar

[86] Li Z T, Zhao Y L, Li Y J, et al. Demonstration of fault localization in optical networks based on knowledge graph and graph neural network. In: Proceedings of Optical Fiber Communication Conference, 2020. Th1F.5. Google Scholar

[87] Lun H Z, Liu X M, Cai M, et al. Anomaly localization in optical transmissions based on receiver DSP and artificial neural network. In: Proceedings of Optical Fiber Communication Conference, 2020. W1K.4. Google Scholar

[88] Yan S Y, Khan F N, Mavromatis A, et al. Field trial of machine-learning-assisted and SDN-based optical network planning with network-scale monitoring database. In: Proceedings of European Conference on Optical Communication, 2017. 1--3. Google Scholar

[89] Christodoulopoulos K, Kokkinos P, Di G A, et al. ORCHESTRA - optical performance monitoring enabling flexible networking. In: Proceedings of International Conference on Transparent Optical Networks, 2015. 1--4. Google Scholar

[90] Wang Z, Zhang M, Wang D. Failure prediction using machine learning and time series in optical network. Opt Express, 2017, 25: 18553-18565 CrossRef PubMed ADS Google Scholar

[91] Boitier F, Lemaire V, Pesic J, et al. Proactive fiber damage detection in real-time coherent receiver. In: Proceedings of European Conference on Optical Communication, 2017. 1--4. Google Scholar

[92] Tanaka T, Kawakami W, Kuwabara S. Intelligent Monitoring of Optical Fiber Bend Using Artificial Neural Networks Trained With Constellation Data. IEEE Netw Lett, 2019, 1: 60-62 CrossRef Google Scholar

[93] Vellido A, Mart'ın-G J D, Lisboa P J G. Making machine learning models interpretable. In: Proceedings of European Symposium on Artificial Neural Networks, 2012. 1--10. Google Scholar

[94] Azzimonti D, Rottondi C, Tornatore M. Reducing probes for quality of transmission estimation in optical networks with active learning. J Opt Commun Netw, 2020, 12: A38 CrossRef Google Scholar

[95] Zhao Y L, Yan B Y, Li Z T, et al. Coordination between control layer AI and on-board AI in optical transport networks [invited]. Journal of Optical Communications and Networking, 2019, 12: A49. Google Scholar

[96] Velasco L, Shariati B, Boitier F. Learning Life Cycle to Speed Up Autonomic Optical Transmission and Networking Adoption. J Opt Commun Netw, 2019, 11: 226-237 CrossRef Google Scholar

Copyright 2020  CHINA SCIENCE PUBLISHING & MEDIA LTD.  中国科技出版传媒股份有限公司  版权所有

京ICP备14028887号-23       京公网安备11010102003388号