来源:信息通信技术与政策
作者:诸葛群碧 钟雪颖 蔡萌 刘晓敏 刘蕾 胡卫生
光纤通信数字孪生系统是智慧全光网的重要数字底座,是增强网络管控能力,实现网络资源最大化利用的重要手段。通过对光纤通信数字孪生系统的相关研究进展进行阐述,给出光纤通信数字孪生系统的架构,重点分析了构建光纤通信数字孪生系统的3个关键技术:灰盒孪生建模、光纤物理层多维融合感知技术、光纤系统在线学习算法和机制。关键词:全光网;光纤通信;数字孪生系统;灰盒建模;多维融合感知;在线学习 中图分类号:TN929.11 文献标识码:A 引用格式:诸葛群碧, 钟雪颖, 蔡萌, 等. 光纤通信数字孪生系统架构及关键技术研究[J]. 信息通信技术与政策, 2021,47(12):86-92. doi:10.12267/j.issn.2096-5931.2021.12.012
0 引言
1 光纤通信数字孪生系统的相关进展
2 光纤通信数字孪生系统的整体架构
图1 光纤通信数字孪生系统架构
3 光纤通信数字孪生系统的关键技术
4 结束语
参考文献
[1] Poggiolini P, Bosco G, Carena A, et al. The GN-model of fiber non-linear propagation and its applications[J]. Journal of Lightwave Technology, 2014,32(4):694-721.
[2] Wang D, Song Y, Li J, et al. Data-driven optical fiber channel modeling: a deep learning approach[J]. Journal of Lightwave Technology, 2020(99):1-1.
[3] Zhu S, Gutterman C L, Mo W, et al. Machine learning based prediction of erbium-doped fiber WDM line amplifier gain spectra[C]//2018 European Conference on Optical Communication(ECOC). IEEE, 2018.
[4] You Y, Jiang Z, Janz C, et al. Machine learning-based EDFA gain model[C]//2018 European Conference on Optical Communication(ECOC). IEEE, 2018.
[5] Zhang B, Zhang R, Zhang Q, et al. Optical filtering penalty estimation using artificial neural network in elastic optical networks with cascaded reconfigurable optical add–drop multiplexers[J]. Optical Engineering, 2019,58(7):1.
[6] Hauske F N, Kuschnerov M, Spinnler B, et al. Optical performance monitoring in digital coherent receivers[J]. Journal of Lightwave Technology, 2011,27(16):3623-3631.
[7] Oda S, Miyabe M, Yoshida S, et al. A learning living network with open ROADMs[J]. Journal of Lightwave Technology, 2017(99):1.
[8] Tanimura T, Hoshida T, Rasmussen J, et al. OSNR monitoring by deep neural networks trained with asynchronously sampled data[C]//Optoelectronics & Communications Conference. IEEE, 2016.
[9] Wang D, Zhang M, Li J, et al. Intelligent constellation diagram analyzer using convolutional neural network-based deep learning[J]. Optics Express, 2017,25(15):17150.
[10] Tanimura T, Hoshida T, Kato T, et al. Convolutional neural network-based optical performance monitoring for optical transport networks[J]. Journal of Optical Communications and Networking, 2019, 11(1):A52.
[11] Meng F, Mavromatis A, Bi Y, et al. Self-learning monitoring on-demand strategy for optical networks[J]. Journal of Optical Communications and Networking, 2019,11(2).
[12] Zhuge Q, Zeng X, Lun H, et al. Application of machine learning in fiber nonlinearity modeling and monitoring for elastic optical networks[C]//2018 European Conference on Optical Communication(ECOC). IEEE, 2018.
[13] Cai M, Zhuge Q, Lun H, et al. Pilot-aided self-phase modulation noise monitoring based on artificial neural network[C]//Asia Communications and Photonics Conference, 2019.
[14] Cai M, Lun H, Fu M, et al. Optical filtering impairment monitoring based on artificial neural network in coherent receiver[C]//Asia Communications and Photonics Conference, 2020.
[15] Mahajan A, Christodoulopoulos K, Martinez R, et al. Modeling EDFA gain ripple and filter penalties with machine learning for accurate QoT estimation[Z]. Journal of Lightwave Technology, 2020.
[16] Liu X, Lun H, Gao R, et al. A data-fusion-assisted telemetry layer for autonomous optical networks[J]. Journal of Lightwave Technology, 2021(99):1-1.
[17] Liu X, Lun H, Fu M, et al. A meta-learning-assisted training framework for AI deployment in optical networks[C]//2020 European Conference on Optical Communications (ECOC), 2020.
Research on architecture and key technologies of digital twin for optical communication
ZHUGE Qunbi, ZHONG Xueying, CAI Meng, LIU Xiaomin, LIU Lei, HU Weisheng
(State Key Laboratory of Advanced Optical Communication Systems and Networks, Shanghai Jiao Tong University, Shanghai 200240, China)
Abstract: Digital twin for optical communication is proposed to build an intelligent optical network, which can help enhance network management and utilize network resources efficiently. In this paper, we first introduce recent researches of digital twin for optical communication and then elaborate on the architecture of it. Afterwards, the key technologies of digital twin including data-driven grey-box modeling , data-fusion-assisted optical telemetry, and online learning algorithms are discussed in detail.
Keywords: all-optical network; optical fiber communication; digital twin; data-driven grey-box modeling; data-fusionassisted telemetry technology; online learning
本文刊于《信息通信技术与政策》2021年 第12期
作者简介
诸葛群碧
钟雪颖
蔡 萌
刘晓敏
刘 蕾
胡卫生