OSNR prediction for optical links via learned noise figures

OSNR prediction for optical links via learned noise figures
复制标题

通过学习噪声系数对光链路进行 OSNR 预测

DOI:
10.1109/ecoc52684.2021.9605932
复制
发表时间:
2021
期刊:
2021 European Conference on Optical Communication (ECOC)
影响因子:
--
通讯作者:
G. Charlet
G. Charlet
中科院分区:
--
文献类型:
--
作者:
Sarah Kamel;H. Hafermann;D. L. Gac;Ludovic Dos Santos;B. Kégl;Y. Frignac;G. Charlet

文献摘要

被引文献

相似文献

我们通过机器学习模型,根据从实验数据中学习到的噪声系数,预测具有多达23个EDFA的光链路的每通道OSNR。对于20跨距链路,覆盖99%情况的误差容限小于0.35 dB。
We predict the per-channel OSNR of optical links with up to 23 EDFAs via a machine learning model based on learned noise figures from experimental data. For a 20 span link, the error margin to cover 99% of cases is less than 0.35 dB.