EUVIMEDEUVIMED entdecken
Crossref

Neural network-assisted joint MFI and OSNR monitoring based on multi-model fitting

Qihan Zhao, Qi Zhang, Xiangjun Xin, Haipeng Yao, Ran Gao, Zhipei Li, Fu Wang, Feng Tian, Xinyu Yuan, Yongjun Wang, Yi Zhao, Zhiqi Huang

Optics Express · 22.09.2025 · 33 (19) · 41194

DOI: 10.1364/oe.576379 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 18.09.2025. Verfasst von Qihan Zhao und 11 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: National Key Research and Development Program of China, the Funds for Creative Research Groups of China, the Program for Youth Innovative Research Team of BUPT.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A neural network-assisted joint modulation format identification (MFI) and optical signal-to-noise ratio (OSNR) estimation method based on multi-model fitting is proposed for elastic optical networks. The method performs MFI by extracting multi-scale amplitude histogram features based on peak-assisted skewed distribution (PASD) fitting. The features are input to a lightweight neural network for robust MFI over a wide OSNR range. For OSNR estimation, a Rician-Gaussian mixture model is used to fit the received signal distribution, with the resulting features processed by a lightweight neural network to achieve accurate and low-complexity estimation. Experimental results in wavelength division multiplexing long-haul systems demonstrate that the proposed method maintains high effectiveness and robustness across varying OSNRs and channel counts. Compared to the transfer-learning cascade neural network (TL-CNN) method, the proposed method achieves 100% MFI accuracy for 4QAM, 16QAM, 32QAM, and 64QAM under minimum OSNR thresholds reduced by 1 dB, 5 dB, 2 dB, and 3 dB, respectively. Furthermore, the system’s OSNR estimation mean absolute error is reduced to 0.091 dB, representing an improvement of more than 58.6% compared to the TL-CNN method. In addition, compared to the TL-CNN method, the proposed method reduces the numbers of multiplications, additions, and network parameters by approximately 85.5%, 91.5%, and 99.3%, respectively. These reductions indicate that the proposed method achieves lower computational complexity and higher efficiency.

Förderung

  • National Key Research and Development Program of China
  • the Funds for Creative Research Groups of China
  • the Program for Youth Innovative Research Team of BUPT
  • National Natural Science Foundation of China

Zitieren

APA

Zhao, Q., Zhang, Q., Xin, X., Yao, H., Gao, R., Li, Z., Wang, F., Tian, F., Yuan, X., Wang, Y., Zhao, Y., & Huang, Z. (2025). Neural network-assisted joint MFI and OSNR monitoring based on multi-model fitting. Optics Express, 33(19), 41194. https://doi.org/10.1364/oe.576379

Vancouver

Zhao Q, Zhang Q, Xin X, Yao H, Gao R, Li Z, et al. Neural network-assisted joint MFI and OSNR monitoring based on multi-model fitting. Optics Express. 2025;33(19):41194. doi:10.1364/oe.576379

BibTeX
@article{Zhao2025,
  author = {Zhao, Qihan and Zhang, Qi and Xin, Xiangjun and Yao, Haipeng and Gao, Ran and Li, Zhipei and Wang, Fu and Tian, Feng and Yuan, Xinyu and Wang, Yongjun and Zhao, Yi and Huang, Zhiqi},
  title = {Neural network-assisted joint MFI and OSNR monitoring based on multi-model fitting},
  journal = {Optics Express},
  year = {2025},
  volume = {33},
  number = {19},
  pages = {41194},
  doi = {10.1364/oe.576379}
}
Kostenlos starten →