Artificial intelligence for optical transport networks: architecture, application and challenges

doi:10.19682/j.cnki.1005-8885.2022.1024

中国邮电高校学报(英文) ›› 2022, Vol. 29 ›› Issue (6): 3-17.doi: 10.19682/j.cnki.1005-8885.2022.1024

• Special Topic: Optical Communication and Artificial Intelligence • 下一篇

Artificial intelligence for optical transport networks: architecture, application and challenges

Li Yajie, Zhang Jie

State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, China

收稿日期:2022-10-21 修回日期:2022-11-08 出版日期:2022-12-30 发布日期:2022-12-30
通讯作者: Li Yajie E-mail:yajieli@bupt.edu.cn
基金资助:
This work was supported by the National Natural Science Foundation of China (61901053, 61831003, 62021005), the

Project of Jiangsu Engineering Research Center of Novel Optical Fiber Technology and Communication Network, Soochow

University (SDGC2117), the Fundamental Research Funds for the Central Universities (2021RC12).

Artificial intelligence for optical transport networks: architecture, application and challenges

Li Yajie, Zhang Jie

State Key Laboratory of Information Photonics and Optical Communications, Beijing University of Posts and Telecommunications, Beijing 100876, China

Received:2022-10-21 Revised:2022-11-08 Online:2022-12-30 Published:2022-12-30
Supported by:
This work was supported by the National Natural Science Foundation of China (61901053, 61831003, 62021005), the

Project of Jiangsu Engineering Research Center of Novel Optical Fiber Technology and Communication Network, Soochow

University (SDGC2117), the Fundamental Research Funds for the Central Universities (2021RC12).

摘要/Abstract

摘要：

Optical network plays an important role in telecommunication networks, which supports high-capacity and long-distance transmission of Internet traffic. However, as the scaling and evolving of optical networks, it faces great challenges in terms of network operation, optimization and maintenance. Artificial intelligence ( AI ) has been proved to have superiority on addressing complex problems, by mimicking cognitive skills similar with human mind. In this paper, we provide a comprehensive investigation of AI applications in optical transport network. First, we give a general AI-based control architecture for optical transport networks. Then, we discuss several typical applications of AI model and algorithms in optical networks. Different use cases are considered, including network planning, quality of transmission ( QoT ) estimation, network reconfiguration, traffic prediction, failure management and so on. In addition, we also present some potential technical challenges for AI application in

optical network for the next years.

关键词: artificial intelligence (AI), optical network, control architecture, typical application

Abstract:

optical network for the next years.

Key words: artificial intelligence (AI), optical network, control architecture, typical application

中图分类号:

TN929.1

Li Yajie, Zhang Jie.

Artificial intelligence for optical transport networks: architecture, application and challenges

[J]. The Journal of China Universities of Posts and Telecommunications, 2022, 29(6): 3-17.

参考文献

1. LI X, LIU Y K, ZHAO Y L, et al. All optical service network for F5G. Proceedings of the IEEE 21st International Conference on Communication Technology (ICCT’21), 2021, Oct 13-16, Tianjin, China. Piscataway, NJ, USA: IEEE, 2022: 710-714.

2. XIE Z Z, HU L, ZHAO K, et al. Topology2Vec: Topology representation learning for data center networking. IEEE Access, 2018, 6: 33840-33848.

3. BISWAS P, AKHTAR M S, SAHA S, et al. Q-learning based energy-efficient network planning in IP-over-EON. IEEE Transactions on Network and Service Management , Early Access, DOI: 10.1109/TNSM.2022.3197329

4. LU W, LIANG L P, KONG B X, et al. AI-assisted knowledge-defined network orchestration for energy-efficient data center networks. IEEE Communications Magazine, 2020, 58(1): 86-92.

5. ZHAO Y L, YAN B Y, LIU D M, et al. SOON: Self-optimizing optical networks with machine learning. Optics Express, 2018, 26(22): 28713-28726.

6. YAN B Y, ZHAO Y L, WANG W, et al. First demonstration of machine-learning-based self-optimizing optical networks (SOON) running on commercial equipment. Proceedings of the 2018 European Conference on Optical Communication (ECOC’18), 2018, Sept 23-27, Rome, Italy. Piscataway, NJ, USA: IEEE, 2018: 3p.

7. ZHAN K X, YANG H, LI J, et al. Intent defined optical network: Toward artificial intelligence-based optical network automation. Proceedings of the 2020 Optical Fiber Communications Conference and Exhibition (OFC’20), 2020, Mar 8-12, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2020: T3J.6.

8. MANSO C, VILALTA R, MUNOZ R, et al. Scalability analysis of machine learning QoT estimators for a cloud-native SDN controller on a WDM over SDM network. Journal of Optical Communications and Networking, 2022, 14(4): 257-266.

9. PROIETTI R, CHEN X L, ZHANG K Q, et al. Experimental demonstration of machine-learning-aided QoT estimation in multi-domain elastic optical networks with alien wavelengths. Journal of Optical Communications and Networking, 2019, 11(1): A1-A10.

10. PANAYIOTOU T, SAVVA G, SHARIATI B, et al. Machine learning for QoT estimation of unseen optical network states. Proceedings of the 2019 Optical Fiber Communications Conference and Exhibition (OFC’19), 2019, Mar 3-7, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2019: Tu2E.2.

11. POUSA R, GEORGIEVA P, PINA J, et al. Machine learning approach for online monitoring of quality of transmission performance indicators in optical fiber networks. Proceedings of the 2021 European Conference on Optical Communication (ECOC’21), 2021, Sept 13-16, Bordeaux, France. Piscataway, NJ, USA: IEEE, 2021: 4p.

12. AZZIMONTI D, ROTTONDI C, TORNATORE M. Using active learning to decrease probes for QoT estimation in optical networks. Proceedings of the 2019 Optical Fiber Communications Conference and Exhibition (OFC’19), 2019, Mar 3-7, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2019: Th1H.1.

13. LU J N, FAN Q R, ZHOU G, et al. Automated training dataset collection system design for machine learning application in optical networks: an example of quality of transmission estimation. Journal of Optical Communications and Networking, 2021, 13(11): 289-300.

14. MARTIN I, HERNANDEZ J A, TROIA S, et al. Is machine learning suitable for solving RWA problems in optical networks? Proceedings of the 2018 European Conference on Optical Communication (ECOC’18), 2018, Sept 23-27, Rome, Italy. Piscataway, NJ, USA: IEEE,2018: 3p.

15. NEVIN J W, NALLAPERUMA S, SHEVCHENKO N A, et al. Techniques for applying reinforcement learning to routing and wavelength assignment problems in optical fiber communication networks. Journal of Optical Communications and Networking, 2022, 14(9): 733-748.

16. ANDREOLETTI D, ROTTONDI C, BIANCO A, et al. A machine learning framework for scalable routing and wavelength assignment in large optical networks. Proceedings of the 2021 Optical Fiber Communications Conference and Exhibition (OFC’21), 2021, Jun 6-11, San Francisco, CA, USA. Piscataway, NJ, USA: IEEE, 2021: F2G.3.

17. TROIA S, RODRIGUEZ A, MARTIN I, et al. Machine-learning-assisted routing in SDN-based optical networks. Proceedings of the 2018 European Conference on Optical Communication (ECOC’18), 2018, Sept 23-27, Rome, Italy. Piscataway, NJ, USA: IEEE, 2018: 3p.

18. CICERI O J, ASTUDILLO C A, ZHU Z Q, et al. Federated learning over next-generation Ethernet passive optical networks. IEEE Network, Early Access, DOI: 10.1109/MNET.111.2100716.

19. LI J, CHEN L, CHEN J J. Enabling technologies for low-latency service migration in 5G transport networks [Invited]. Journal of Optical Communications and Networking, 2021, 13(2): A200-A210.

20. CHEN X L, PROIETTI R, YOO S J B. Building autonomic elastic optical networks with deep reinforcement learning. IEEE Communications Magazine, 2019, 57(10): 20-26.

21. CHEN X L, GUO J N, ZHU Z Q, et al. DeepRMSA: A deep-reinforcement-learning routing, modulation and spectrum assignment agent for elastic optical networks. Proceedings of the 2018 Optical Fiber Communications Conference and Exhibition (OFC’18), 2018, Mar 11-15, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2018: W4F.2.

22. CHEN X L, LI B J, PROIETTI R, et al. DeepRMSA: A deep reinforcement learning framework for routing, modulation and spectrum assignment in elastic optical networks. Journal of Lightwave Technology, 2019, 37(16): 4155-4163.

23. XU L F, HUANG Y C, XUE Y, et al. Deep reinforcement learning-based routing and spectrum assignment of EONs by exploiting GCN and RNN for feature extraction. Journal of Lightwave Technology, 2022, 40(15): 4945-4955.

24. LUO X, SHI C, WANG L Q, et al. Leveraging double-agent-based deep reinforcement learning to global optimization of elastic optical networks with enhanced survivability. Optics Express, 2019, 27(6): 7896-7911.

25. HAJIPOUR S, HABIBI M, BEYRANVAND H. Artificial neural network aided multiclass service provisioning and prioritization in EONs. IEEE Transactions on Network and Service Management, Early Access, DOI: 10.1109/TNSM.2022.3183500.

26. SINGH S K, JUKAN A. Machine-learning-based prediction for resource (Re)allocation in optical data center networks. Journal of Optical Communications and Networking, 2018, 10(10): D12-D28.

27. YU A, YANG H, BAI W, et al. Leveraging deep learning to achieve efficient resource allocation with traffic evaluation in datacenter optical networks. Proceedings of the 2018 Optical Fiber Communications Conference and Exhibition (OFC’18), 2018, Mar 11-15, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2018: W4I.2.

28. LI B J, ZHU Z Q. GNN-based hierarchical deep reinforcement learning for NFV-oriented online resource orchestration in elastic optical DCIs. Journal of Lightwave Technology, 2022, 40(4): 935-946.

29. ZHU R J, LI S H, WANG P S, et al. Deep reinforced energy efficient traffic grooming in fog-cloud elastic optical networks. Proceedings of the 2020 Optical Fiber Communications Conference and Exhibition (OFC’20), 2020, Mar 8-12, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2020: M1A.4.

30. GUAN L Y, ZHANG M, GUI Y H, et al. AI-assisted intent-based traffic grooming in a dynamically shared 5G optical fronthaul network. Optics Express, 2021, 29(15): 23113-23130.

31. MARTÍN I, TROIA S, HERNANDEZ J A, et al. Machine learning-based routing and wavelength assignment in software-defined optical networks. IEEE Transactions on Network and Service Management, 2019, 16(3): 871-883.

32. TIAN X J, LI B J, GU R T, et al. Reconfiguring multicast sessions in elastic optical networks adaptively with graph-aware deep reinforcement learning. Journal of Optical Communications and Networking, 2021, 13(11): 253-265.

33. PROIETTI R, LIU C Y, CHEN X L, et al. Machine-learning-aided bandwidth and topology reconfiguration for optical data center networks. Proceedings of the 2021 Optical Fiber Communications Conference and Exhibition (OFC’21), 2021, Jun 6-11, San Francisco, CA, USA. Piscataway, NJ, USA: IEEE, 2021: W4A.4.

34. LIU C Y, CHEN X L, LI Z H, et al. SL-Hyper-FleX: A cognitive and flexible-bandwidth optical datacom network by self-supervised learning [Invited]. Journal of Optical Communications and Networking, 2022, 14(2): A113-A121.

35. TRINDADE S, DA FONSECA N L S. Machine learning for spectrum defragmentation in space-division multiplexing elastic optical networks. IEEE Network, 2021, 35(1): 326-332.

36. JANA R K, CHATTERJEE B C, SINGH A P, et al. Machine learning-assisted nonlinear-impairment-aware proactive defragmentation for C+L band elastic optical networks. Journal of Optical Communications and Networking, 2022, 14(3): 56-68.

37. YAN S J, ZHU Z Y, GLICK M S, et al. Accelerating distributed machine learning in disaggregated architectures with flexible optically interconnected computing resources. Proceedings of the 2022 Optical Fiber Communications Conference and Exhibition (OFC’22), 2022, Mar 6-10, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2022: Th1G.2.

38. LIU S Q, NIU B, LI D Y, et al. DL-assisted cross-layer orchestration in software-defined IP-Over-EONs: From algorithm design to system prototype. Journal of Lightwave Technology, 2019, 37(17): 4426-4438.

39. BALANICI M, PACHNICKE S. Machine learning-based traffic prediction for optical switching resource allocation in hybrid intra-data center networks. Proceedings of the 2019 Optical Fiber Communications Conference and Exhibition (OFC’19), 2019, Mar 3-7, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2019: Th1H.4.

40. CHEN X L, GUO J L, ZHU Z Q, et al. Leveraging deep learning to achieve knowledge-based autonomous service provisioning in broker-based multi-domain SD-EONs with proactive and intelligent predictions of multi-domain traffic. Proceedings of the 2017 European Conference on Optical Communication (ECOC’17), 2017, Sept 17-21, Gothenburg, Sweden. Piscataway, NJ, USA: IEEE, 2017: 3p.

41. GUO J N, ZHU Z Q. When deep learning meets inter-datacenter optical network management: Advantages and vulnerabilities. Journal of Lightwave Technology, 2018, 36(20): 4761-4773.

42. PANAYIOTOU T, ELLINAS G. Addressing traffic prediction uncertainty in multi-period planning optical networks. Proceedings of the 2022 Optical Fiber Communications Conference and Exhibition (OFC’22), 2022, Mar 6-10, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2022: M3F.2.

43. CHOUDHURY G, LYNCH D, THAKUR G, et al. Two use cases of machine learning for SDN-enabled ip/optical networks: Traffic matrix prediction and optical path performance prediction [Invited]. Journal of Optical Communications and Networking, 2018, 10(10): D52-D62.

44. SONG H K, LI Y J, LIU M Z, et al. Experimental study of machine-learning-based detection and location of eavesdropping in end-to-end optical fiber communications. Optical Fiber Technology, 2022, 68: Article 102669.

45. LIU M Z, LI Y J, SONG H K, et al. Experimental demonstration of optical fiber eavesdropping detection based on deep learning. Proceedings of the 2019 Asia Communications and Photonics Conference (ACP’19), 2019, Nov 2-5, Chengdu, China. Piscataway, NJ, USA: IEEE, 2019: 3p.

46. LI Y L, HUA N, LI J D, et al. Optical spectrum feature analysis and recognition for optical network security with machine learning. Optics Express, 2019, 27(17): 24808-24827.

47. FURDEK M, NATALINO C, DI GIGLIO A, et al. Optical network security management: Requirements, architecture, and efficient machine learning models for detection of evolving threats [Invited]. Journal of Optical Communications and Networking, 2021, 13(2): A144-A155.

48. WANG M, LU H C, LIU S Q, et al. How to mislead AI-assisted network automation in SD-IPoEONs: A comparison study of DRL- and GAN-based approaches. Journal of Lightwave Technology, 2020, 38(20): 5574-5585.

49. PAN X Q, YANG H, XU Z C, et al. Adversarial analysis of ML-based anomaly detection in multi-layer network automation. Journal of Lightwave Technology, 2022, 40(15): 4934-4944.

50. CHEN X L, LI B J, PROIETTI R, et al. Self-taught anomaly detection with hybrid unsupervised/supervised machine learning in optical networks. Journal of Lightwave Technology, 2019, 37(7): 1742-1749.

51. SHAHKARAMI S, MUSUMECI F, CUGINI F, et al. Machine-learning-based soft-failure detection and identification in optical networks. Proceedings of the 2018 Optical Fiber Communications Conference and Exposition (OFC’18), Mar 11-15, 2018, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2018: M3A.5.

52. WANG Z L, ZHANG M, WANG D S, et al. Failure prediction using machine learning and time series in optical network. Optics Express, 2017, 25(16): 18553-18565.

53. MUSUMECI F. Machine learning for failure management in optical networks. Proceedings of the 2021 Optical Fiber Communications Conference and Exhibition (OFC’21), 2021, Jun 6-10, San Francisco, CA, USA. Piscataway, NJ, USA: IEEE, 2021: Th4J.1.

54. RAFIQUE D, SZYRKOWIEC T, GRIEßER H, et al. Cognitive assurance architecture for optical network fault management. Journal of Lightwave Technology, 2018, 36(7): 1443-1450.

55. SILVA M F, PACINI A, SGAMBELLURI A, et al. Learning long-and short-term temporal patterns for ML-driven fault management in optical communication networks. IEEE Transactions on Network and Service Management, 2022, 19(3): 2195-2206.

56. LI Z T, ZHAO Y L, LI Y J, et al. Fault localization based on knowledge graph in software-defined optical networks. Journal of Lightwave Technology, 2021, 39(13): 4236-4246.

57. HERNÁNDEZ-CHULDE C, CASELLAS R, MARTÍNEZ R, et al. Evaluation of deep reinforcement learning for restoration in optical networks. Proceedings of the 2022 Optical Fiber Communications Conference and Exhibition (OFC’22), 2022, Mar 6-10, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2022: Th2A.19.

58. ZHAO Z P, ZHAO Y L, LI Y J, et al. Service restoration in multi-modal optical transport networks with reinforcement learning. Optics Express, 2021, 29(3): 3825-3840.

59. LIAN M, GU R T, QU Y Y, et al. Flexible optical network enabled hybrid recovery for edge network with reinforcement learning. Proceedings of the 2020 Optical Fiber Communications Conference and Exhibition (OFC’20), 2020, Mar 8-12, San Francisco, CA, USA. Piscataway, NJ, USA: IEEE, 2020: M1A.2.

60. TANG S F, KONG J W, NIU B, et al. Programmable multilayer INT: An enabler for AI-assisted network automation. IEEE Communications Magazine, 2020, 58(1): 26-32.

61. CHEN X L, LIU C Y, PROIETTI R, et al. Automating optical network fault management with machine learning. IEEE Communications Magazine, Early Access, DOI: 10.1109/MCOM.003.2200110.

62. CHO J Y, PEDRENO-MANRESA, J J, PATRI S, et al. DeepALM: Holistic optical network monitoring based on machine learning. Proceedings of the 2022 Optical Fiber Communications Conference and Exhibition (OFC’22), 2022, Mar 06-10, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2022: M3Z.11.

63. MUSUMECI F, ROTTONDI C, CORANI G, et al. A tutorial on machine learning for failure management in optical networks. Journal of Lightwave Technology, 2019, 37(16): 4125-4139.

64. CHEN X L, PROIETTI R, LIU C Y, et al. Towards self-driving optical networking with reinforcement learning and knowledge transferring. Proceedings of the 2020 International Conference on Optical Network Design and Modeling (ONDM’20), 2020, May 18-21, Castelldefels, Spain. Piscataway, NJ, USA: IEEE, 2020: 3p.

65. KHAN I, BILAL M, UMAR MASOOD M, et al. Lightpath QoT computation in optical networks assisted by transfer learning. Journal of Optical Communications and Networking, 2021, 13(4): B72-B82.

66. ZHANG B, ZHAO Y L, LI Y J, et al. Transfer learning aided concurrent multi-alarm prediction in optical transport networks. Proceedings of the 2020 Asia Communications and Photonics Conference (ACP’20) and International Conference on Information Photonics and Optical Communications (IPOC’20), 2020, Oct 24-27, Beijing, China. Piscataway, NJ, USA: IEEE, 2020: 3p.

67. PÉREZ-SUAY A, ADSUARA, J E, PILES M, et al. Interpretability of recurrent neural networks in remote sensing. Proceedings of the 2020 IEEE International Geoscience and Remote Sensing Symposium (IGARSS’20), 2020, Sept 26-Oct 2, Waikoloa, HI, USA. Piscataway, NJ, USA: IEEE, 2020: 3991-3994.

68. ZHANG C Y, WANG D S, SONG C, et al. Interpretable learning algorithm based on XGBoost for fault prediction in optical network. Proceedings of the 2020 Optical Fiber Communications Conference and Exhibition (OFC’20), 2020, Mar 8-12, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2020: Th1F.3.

69. PEDRYCZ W. Design, interpretability, and explainability of models in the framework of granular computing and federated learning. Proceedings of the 3rd IEEE Conference on Norbert Wiener in the 21st Century (21CW’21), 2021, Jul 22-25, Chennai, India. Piscataway, NJ, USA: IEEE, 2021: 6p.

70. ZHENG S H, XIAO X, LI Y J, et al. Deep reinforcement learning based DNN model partition in edge computing-enabled metro optical network. Proceedings of the 2022 Asia Communications and Photonics Conference (ACP’21), 2021, Oct 24-27, Shanghai, China. Piscataway, NJ, USA: IEEE, 2021: 3p.

71. GHOBADI M. Emerging optical interconnects for AI Systems. Proceedings of the 2022 Optical Fiber Communications Conference and Exhibition (OFC’22), 2022, Mar 6-10, San Diego, CA, USA. Piscataway, NJ, USA: IEEE, 2022: Th1G.1.

72. 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. Proceedings of the 2020 Optical Fiber Communications Conference and Exhibition (OFC’20), 2020, Mar 8-12, San Diego, CA. Piscataway, NJ, USA: IEEE, 2020: M1B.3.

73. LI C, YANG H, YAO Q, et al. High-precision edge-cloud collaboration with federated learning in edge optical network. Proceedings of the 2021 Optical Fiber Communications Conference and Exhibition (OFC), 2021, Jun 6-10, San Francisco, CA, USA. Piscataway, NJ, USA: IEEE, 2021: W6A.11.

Artificial intelligence for optical transport networks: architecture, application and challenges

Artificial intelligence for optical transport networks: architecture, application and challenges

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价