Role of Digital Twin in Optical Communication: Fault Management, Hardware Configuration, and Transmission Simulation

Optical communication is developing rapidly in the directions of hardware resource diversification, transmission system flexibility, and network function virtualization. Its proliferation poses a significant challenge to traditional optical communication management and control systems. Digital twin (DT), a technology that utilizes data, models, and algorithms and integrates multiple disciplines, acts as a bridge between the real and virtual worlds for comprehensive connectivity. In the digital space, virtual models are stablished dynamically to simulate and describe the states, behaviors, and rules of physical objects in the physical space. DT has been significantly developed and widely applied in industrial and military fields. This study introduces the DT technology to optical communication through interdisciplinary crossing and proposes a DT framework suitable for optical communication. The intelligent fault management model, flexible hardware configuration model, and dynamic transmission simulation model are established in the digital space with the help of deep learning algorithms to ensure the highreliability operation and high-efficiency management of optical communication systems and networks.

[1]  S. Michael Spottswood,et al.  Reengineering Aircraft Structural Life Prediction Using a Digital Twin , 2011 .

[2]  Luca Fumagalli,et al.  Flexible Automation and Intelligent Manufacturing , FAIM 2017 , 27-30 June 2017 , Modena , Italy A review of the roles of Digital Twin in CPS-based production systems , 2017 .

[3]  Chao Lu,et al.  An Optical Communication's Perspective on Machine Learning and Its Applications , 2019, Journal of Lightwave Technology.

[4]  Min Zhang,et al.  Interpretable Learning Algorithm Based on XGBoost for Fault Prediction in Optical Network , 2020, 2020 Optical Fiber Communications Conference and Exhibition (OFC).

[5]  Danshi Wang,et al.  Digital twin-enabled self-evolved optical transceiver using deep reinforcement learning. , 2020, Optics letters.

[6]  Min Zhang,et al.  Temporal data-driven failure prognostics using BiGRU for optical networks , 2020, IEEE/OSA Journal of Optical Communications and Networking.

[7]  Fei Tao,et al.  Digital twin-driven product design, manufacturing and service with big data , 2017, The International Journal of Advanced Manufacturing Technology.

[8]  Xue Chen,et al.  Deep learning based adaptive sequential data augmentation technique for the optical network traffic synthesis. , 2019, Optics express.

[9]  Li Deng,et al.  A tutorial survey of architectures, algorithms, and applications for deep learning , 2014, APSIPA Transactions on Signal and Information Processing.

[10]  He Zhang,et al.  Digital Twin in Industry: State-of-the-Art , 2019, IEEE Transactions on Industrial Informatics.

[11]  Elio Salvadori,et al.  Cognitive dynamic optical networks [invited] , 2013, IEEE/OSA Journal of Optical Communications and Networking.

[12]  I. Tomkos,et al.  Cognitive dynamic optical networks , 2013, 2013 Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference (OFC/NFOEC).

[13]  Marco Ruffini,et al.  An Overview on Application of Machine Learning Techniques in Optical Networks , 2018, IEEE Communications Surveys & Tutorials.

[14]  Jingjing Yao,et al.  Highly efficient data migration and backup for big data applications in elastic optical inter-data-center networks , 2015, IEEE Network.

[15]  Xue Chen,et al.  Data-driven Optical Fiber Channel Modeling: A Deep Learning Approach , 2020, Journal of Lightwave Technology.

[16]  Wei Lu,et al.  Dynamic Service Provisioning in Elastic Optical Networks With Hybrid Single-/Multi-Path Routing , 2013, Journal of Lightwave Technology.