Abstract

Deep neural networks (DNNs) have been successfully applied for accurate optical signal-to-noise ratio (OSNR) monitoring. However, the performance of OSNR monitoring substantially degrades when a mega dataset is inaccessible. Here, we demonstrate an accurate OSNR monitoring scheme based on a data-augmentation (DA)-assisted DNN with a small-scale dataset. When a 20 GBaud quadrature phase shift keying (QPSK) signal is transmitted over 400 to 2600 km standard single-mode fiber (SSMF) with an OSNR range from 8 to 14 dB, we experimentally evaluate the minimum dataset size to secure a mean absolute error (MAE) of OSNR monitoring less than 1 dB. The DA-assisted scheme only requires 50% of the raw data, in comparison with the traditional DNN scheme. Thus, the DA-assisted DNN scheme is promising for field-trial accurate OSNR monitoring, especially when the collection of mega datasets is inconvenient.

© 2021 Optica Publishing Group

Nonlinear SNR estimation based on the data augmentation-assisted DNN with a small-scale dataset

Weiwei Zhao, Yijun Cheng, Meng Xiang, Ming Tang, Yuwen Qin, and Songnian Fu
Opt. Express 30(22) 39725-39735 (2022)

Meta-learning-enabled accurate OSNR monitoring of directly detected QAM signals with one-shot training

Yijun Cheng, Zheng Yang, Zhijun Yan, Deming Liu, Songnian Fu, and Yuwen Qin
Opt. Lett. 47(9) 2218-2221 (2022)

Guideline of choosing optical delay time to optimize the performance of an interferometry-based in-band OSNR monitor

Zhuili Huang, Jifang Qiu, Sheng Wang, Xue Ji, Ye Tian, Deming Kong, Miao Yu, and Jian Wu
Opt. Lett. 41(18) 4178-4181 (2016)

Experimental demonstration of robustness and accuracy of a DLI-based OSNR monitor under changes in the transmitter and link for different modulation formats and baud rates

Ahmed Almaiman, Mohammad Reza Chitgarha, Wajih Daab, Morteza Ziyadi, Amirhossein Mohajerin-Ariaei, Salman Khaleghi, Moshe Willner, Vijay Vusirikala, Xiaoxue Zhao, Dan Kilper, Loukas Paraschis, Atiyah Ahsan, Michael Wang, Keren Bergman, Moshe Tur, Joseph D. Touch, and Alan E. Willner
Opt. Lett. 40(9) 2012-2015 (2015)

Knowledge distillation technique enabled hardware efficient OSNR monitoring from directly detected PDM-QAM signals

Junjiang Xiang, Yijun Cheng, Shiwen Chen, Meng Xiang, Yuwen Qin, and Songnian Fu
J. Opt. Commun. Netw. 14(11) 916-923 (2022)