Digital twin modeling and controlling of optical power evolution enabling autonomous-driving optical networks:a Bayesian approach

作     者：Xiaomin Liu Yihao Zhang Yuli Chen Yichen Liu Meng Cai Qizhi Qiu Mengfan Fu Lilin Yi Weisheng Hu Qunbi Zhuge 

作者机构：Shanghai Jiao Tong UniversityState Key Laboratory of Advanced Optical Communication Systems and NetworksDepartment of Electronic EngineeringShanghaiChina 

出 版 物：《Advanced Photonics》 (先进光子学（英文）)

年 卷 期：2024年第6卷第2期

页      面：69-80页

核心收录：

学科分类：08[工学] 0803[工学-光学工程] 0702[理学-物理学] 

基　　金：supported by the Shanghai Pilot Program for Basic Research-Shanghai Jiao Tong University(Grant No.21TQ1400213) the National Natural Science Foundation of China(Grant No.62175145) 

主　　题：optical fiber communications digital twin Bayesian inference optical amplifiers autonomous-driving optical networks 

摘      要：Optical networks are evolving toward ultrawide bandwidth and autonomous *** this scenario,it is crucial to accurately model and control optical power evolutions(OPEs)through optical amplifiers(OAs),as they directly affect the signal-to-noise ratio and fiber ***,a fundamental contradiction arises between the complex physical phenomena in optical transmission and the required precision in network *** theoretical methods underperform due to ideal assumptions,while data-driven approaches entail exorbitant costs associated with acquiring massive amounts of data to achieve the desired level of *** this work,we propose a Bayesian inference framework(BIF)to construct the digital twin of OAs and control OPE in a data-efficient *** the informative data are collected to balance the exploration and exploitation of the data space,thus enabling efficient autonomous-driving optical networks(ADONs).Simulations and experiments demonstrate that the BIF can reduce the data size for modeling erbium-doped fiber amplifiers by 80%and Raman amplifiers by 60%.Within 30 iterations,the optimal controlling performance can be achieved to realize target signal/gain profiles in links with different types of *** results show that the BIF paves the way to accurately model and control OPE for future ADONs.