Abstract

To comprehensively assess the conditions of an optical fiber communication system, it is essential to implement joint estimation of the following four critical impairments: nonlinear signal-to-noise ratio (${{\rm SNR}_{\rm{NL}}}$), optical signal-to-noise ratio (OSNR), chromatic dispersion (CD), and differential group delay (DGD). However, current studies only achieve identifying a limited number of impairments within a narrow range, due to a lack of high-performance computing algorithms and a unified representation of impairments. To address these challenges, we adopt time-frequency signal processing based on the fractional Fourier transform (FrFT) to achieve the unified representation of impairments, while employing a Transformer-based neural network (NN) to break through network performance limitations. To verify the effectiveness of the proposed estimation method, numerical simulations were conducted on a five-channel polarization-division-multiplexed quadrature phase shift keying (PDM-QPSK) long haul optical transmission system with the symbol rate of 50 GBaud per channel. The mean absolute error (MAE) for ${\rm SNR}_{\rm NL}$, OSNR, CD, and DGD estimation is 0.091 dB, 0.058 dB, 117 ps/nm, and 0.38 ps, and the monitoring window ranges from ${0}{-}{20}\;{\rm dB}$, ${10}{-}{30}\;{\rm dB}$, ${1700}{-}{51{,}000}\;{\rm ps/nm}$, and ${0}{-}{100}\;{\rm ps}$, respectively. Our proposed method achieves accurate estimation of linear and nonlinear impairments over a broad range, representing a significant advancement in the field of optical performance monitoring (OPM).

© 2024 Optica Publishing Group

Joint nonlinear optical signal-to-noise ratio estimation and modulation format identification based on constellation-points trajectory information and multitask 1DCNN for WDM systems

Zhiguo Wang, Chenglin Bai, Lishan Yang, Xinyu Chi, Peng Qin, Xueyuan Luo, Hengying Xu, and Peiyun Ge
Appl. Opt. 61(36) 10744-10754 (2022)

Fast signal quality monitoring for coherent communications enabled by CNN-based EVM estimation

Yuchuan Fan, Aleksejs Udalcovs, Xiaodan Pang, Carlos Natalino, Marija Furdek, Sergei Popov, and Oskars Ozolins
J. Opt. Commun. Netw. 13(4) B12-B20 (2021)

DNN-based optical performance monitoring and its application for soft failure localization by multipoint estimation

Takafumi Tanaka, Tetsuro Inui, and Shingo Kawai
J. Opt. Commun. Netw. 14(11) 894-902 (2022)

Machine Learning Based Linear and Nonlinear Noise Estimation

F. J. Vaquero Caballero, D. J. Ives, C. Laperle, D. Charlton, Q. Zhuge, M. O’Sullivan, and Seb J. Savory
J. Opt. Commun. Netw. 10(10) D42-D51 (2018)

Convolutional Neural Network-Based Optical Performance Monitoring for Optical Transport Networks

Takahito Tanimura, Takeshi Hoshida, Tomoyuki Kato, Shigeki Watanabe, and Hiroyuki Morikawa
J. Opt. Commun. Netw. 11(1) A52-A59 (2019)