[1] [1] KAUSHAL H, KADDOUM G. Optical communication in space: challenges and mitigation techniques[J]. IEEE Communications Surveys & Tutorials, 2016, 19(1): 57-96.

[2] [2] KHALIGHI M A, UYSAL M. Survey on free space optical communication: a communication theory perspective [J]. IEEE Communications Surveys & Tutorials, 2014, 16(4): 2231-2258.

[3] [3] ZHAO Y, WANG Y, WANG W, et al. Software-defined optical networking (SDON): principles and applications[M]. Rijeka: InTech, 2017.

[4] [4] JI P N. Software defined optical network[C]//The 2012 11th International Conference on Optical Communications and Networks(ICOCN), November 28-30, 2012, Pattaya, Thailand. Pattaya: IEEE, 2012: 1-4.

[5] [5] NSAFOA Y K, TCHAO E T, YEBOAH-AKOWUAH B, et al. Soft-ware-defined networks for optical networks using flexible orchestration: advances, challenges, and opportunities [J]. Journal of Computer Networks and Communications, 2022(1): 1-40.

[6] [6] LIU P, JI W, LIU Q, et al. Failure prediction based on LSTM and SVM under SDON architecture [C]//2021 7th International Conference on Computer and Communications(ICCC), December 10-13, 2021, Chengdu, China. Chengdu: IEEE, 2021: 398-402.

[7] [7] JHA R K, LLAH B N M. Software defined optical networks (SDON):proposed architecture and comparative analysis[J]. Journal of the European Optical Society-Rapid Publications, 2019, 15(1): 1-15.

[8] [8] WANG M, CUI Y, WANG X, et al. Machine learning for networking:Workflow, advances and opportunities[J]. IEEE Network, 2017, 32(2): 92-99.

[9] [9] MESTRES A, ALARCON E, JI Y, et al. Understanding the modeling of computer network delays using neural networks[C]//2018 Workshop on Big Data Analytics and Machine Learning for Data Communication Networks,August 20, 2018, Budapest, Hungary. New York: Association for Computing Machinery, 2018: 46-52.

[10] [10] VALADARSKY A, SCHAPIRA M, SHAHAF D, et al. Learning to route [C]//16th ACM workshop on hot topies in networks, November 30-December 1, 2017, Palo Alto, USA. New York: Association for Computing Machinery, 2017: 185-191.

[11] [11] XIAO S, HE D, GONG Z. Deep-q: traffic-driven qos inference using deep generative network[C]//2018 Workshop on Network Meets AI & ML,August 24, 2018, Budapest, Hungary. New York: Association for Computing Machinery, 2018: 67-73.

[12] [12] CHEN X, GUO J, ZHU Z, et al. Deep-RMSA: a deep-reinforcement-learning routing, modulation and spectrum assignment agent for elastic optical networks[C]//Optical Fiber Communication Conference, March 11-15,2018, San Diego, USA. New York: Optica Publishing Group, 2018: 1-3.

[13] [13] GEYER F, BONDORF S. DeepTMA: predicting effective contention models for network calculus using graph neural networks [C]//IEEE INFO-COM 2019-IEEE Conference on Computer Communications, April 29 -May 2, 2019, Paris, France. New York: IEEE, 2019: 1009-1017.

[14] [14] RUSEK K, SUAREZ-VARELA J, MESTRES A, et al. Unveiling the potential of graph neural networks for network modeling and optimization in SDN [C]//2019 ACM Symposium on SDN Research, April 3-4, 2019,San Jose, USA: Association for Computing Machinery, 2019: 140-151.

[15] [15] RUSEK K, SUAREZ-VARELA J, ALMASAN P, et al. Routenet:leveraging graph neural networks for network modeling and optimization in SDN [J]. IEEE Journal on Selected Areas in Communications, 2020, 38(10): 2260-2270.

[16] [16] HOCHREITER S, SCHMIDHUBER J. Long short-term memory [J].Neural Computation, 2010, 9(8): 1735-1780.

[17] [17] CHUNG J, GULCEHRE C, CHO K H, et al. Gated feedback recurrent neural networks [C]//32nd International Conference on Machine Learning,July 6-11, 2015, Lille, France. Cambridge: JMLR.org, 2015, 37: 2067 -2075.