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