EUVIMEDEUVIMED entdecken
Crossref

Constellation Density Matrix and Lightweight Multi-Task Pruning Model-Based Joint Optical Performance Monitoring in PCS-EON Systems

Fan Yang, Hao Zhou, Du Tang, Yingjie Jiang, Yutao Zhou, Baoxuan Quan, Hengying Xu, Chenglin Bai, Yaojun Qiao

Journal of Lightwave Technology · 2026-11 · 44 (21) · 9528-9535

DOI: 10.1109/jlt.2026.3733107 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Lightwave Technology, 2026-11. Verfasst von Fan Yang und 8 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Youth Project Fund of China Academy of Information and Communications Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes a novel joint optical performance monitoring (OPM) scheme for rate-adaptive probabilistic constellation shaping elastic optical network (PCS-EON) systems, simultaneously enabling entropy estimation, optical signal-to-noise ratio (OSNR) estimation, and modulation format identification (MFI). The scheme integrates the constellation density matrix (CDM) feature with a lightweight weight-optimized multi-task pruning (WO-MTP) model. The CDM feature transforms discrete symbols into a two-dimensional density matrix to reduce input dimensionality and extract key features. The lightweight WO-MTP model removes low-contribution weights through pruning and optimization. The scheme is validated by 130-GBaud simulations and 64-GBaud experiments in PDM PCS-16QAM/64QAM systems. The simulation results demonstrate 100% MFI accuracy, with mean absolute errors below 0.032 b/symbol for entropy estimation and 0.29 dB for OSNR estimation, while the experimental results further confirm the effectiveness of the proposed scheme. In terms of computational complexity, it reduces both floating-point operations (FLOPs) and parameters (Params) by about 85% compared with the baseline model, requiring only 0.7651 M FLOPs and 0.0897 M Params. These results indicate its potential for deployment in resource-constrained edge optical network nodes.

Förderung

  • National Natural Science Foundation of China
  • Youth Project Fund of China Academy of Information and Communications Technology

Zitieren

APA

Yang, F., Zhou, H., Tang, D., Jiang, Y., Zhou, Y., Quan, B., Xu, H., Bai, C., & Qiao, Y. (2026). Constellation Density Matrix and Lightweight Multi-Task Pruning Model-Based Joint Optical Performance Monitoring in PCS-EON Systems. Journal of Lightwave Technology, 44(21), 9528-9535. https://doi.org/10.1109/jlt.2026.3733107

Vancouver

Yang F, Zhou H, Tang D, Jiang Y, Zhou Y, Quan B, et al. Constellation Density Matrix and Lightweight Multi-Task Pruning Model-Based Joint Optical Performance Monitoring in PCS-EON Systems. Journal of Lightwave Technology. 2026;44(21):9528-9535. doi:10.1109/jlt.2026.3733107

BibTeX
@article{Yang2026,
  author = {Yang, Fan and Zhou, Hao and Tang, Du and Jiang, Yingjie and Zhou, Yutao and Quan, Baoxuan and Xu, Hengying and Bai, Chenglin and Qiao, Yaojun},
  title = {Constellation Density Matrix and Lightweight Multi-Task Pruning Model-Based Joint Optical Performance Monitoring in PCS-EON Systems},
  journal = {Journal of Lightwave Technology},
  year = {2026},
  volume = {44},
  number = {21},
  pages = {9528--9535},
  doi = {10.1109/jlt.2026.3733107}
}
Kostenlos starten →