Nonlinear compensation using a robust neural network for noisy samples in a high-speed coherent optical transceiver
Optics Express · 06.04.2026 · 34 (7) · 11951
DOI: 10.1364/oe.589389 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 24.03.2026. Verfasst von Zicai Cao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Nature Science Foundation of China, Shenzhen Science and Technology Program.
Abstract (Originalsprache)
Nonlinear impairments in coherent optical transceivers are the primary bottleneck for enhancing transmission capacity. However, as most of the recently prevalent nonlinear equalizers (NLE) are data-driven, their dependence on training signal quality and the incompatibility between their machine-learning frameworks and communication scenarios have contributed to the potential risks of their applications. Therefore, this paper aims to improve the deficiency of NLEs and enhance their practical possibilities. We focus on the neural network (NN)-based nonlinear equalizers (NNLE) and extend the meta-training methods to improve the training methodology in the basic NLEs’ framework. A noisy-samples-robust NN (NSNN) based NLE architecture is proposed. With a bilevel optimization based on meta-learning to train an affiliate model for noisy samples purification, the proposed NSNN can be efficiently trained under data sets with a sufficient amount of noisy samples mixed in. Thus, it can provide reliable performance in many scenarios where traditional NLEs’ performance is limited. We experimentally demonstrate its effectiveness in nonlinear impairments in a high-speed coherent optical transceiver, and its performance is compared with representative traditional NLEs. In a dual-polarization probabilistic constellation shaping 128 QAM back-to-back transmission with a net bitrate over 1 Tbps, the proposed NSNN can provide an optical signal-to-noise (OSNR) gain of over 1.5 dB at the 24% soft-decision forward error correction threshold of 4.5e-2. The results also illustrate that the proposed NSNN can provide stable gains at acceptable complexity cost under various test conditions, and achieve more stable generalizability than common NLEs.
Förderung
- National Key Research and Development Program of China
- National Nature Science Foundation of China
- Shenzhen Science and Technology Program
Zitieren
APA
Cao, Z., Zhang, Z., Chen, Y., Cheng, M., Yang, Q., Tang, M., Liu, D., & Deng, L. (2026). Nonlinear compensation using a robust neural network for noisy samples in a high-speed coherent optical transceiver. Optics Express, 34(7), 11951. https://doi.org/10.1364/oe.589389
Vancouver
Cao Z, Zhang Z, Chen Y, Cheng M, Yang Q, Tang M, et al. Nonlinear compensation using a robust neural network for noisy samples in a high-speed coherent optical transceiver. Optics Express. 2026;34(7):11951. doi:10.1364/oe.589389
BibTeX
@article{Cao2026,
author = {Cao, Zicai and Zhang, Ziheng and Chen, Yifu and Cheng, Mengfan and Yang, Qi and Tang, Ming and Liu, Deming and Deng, Lei},
title = {Nonlinear compensation using a robust neural network for noisy samples in a high-speed coherent optical transceiver},
journal = {Optics Express},
year = {2026},
volume = {34},
number = {7},
pages = {11951},
doi = {10.1364/oe.589389}
}
EUVIMED