The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Sep. 28, 2021

Filed:

Nov. 29, 2020
Applicant:

Nec Laboratories America, Inc., Princeton, NJ (US);

Inventors:

Yue-Kai Huang, Princeton, NJ (US);

Shaoliang Zhang, Princeton, NJ (US);

Ezra Ip, West Windsor, NJ (US);

Jiakai Yu, Tuscon, AZ (US);

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
H04B 10/079 (2013.01); G06N 3/04 (2006.01); H04L 27/34 (2006.01); H04B 10/07 (2013.01);
U.S. Cl.
CPC ...
H04B 10/07953 (2013.01); G06N 3/0454 (2013.01); H04B 10/07 (2013.01); H04B 10/079 (2013.01); H04B 10/0795 (2013.01); H04L 27/3405 (2013.01);
Abstract

Aspects of the present disclosure describe systems, methods. and structures in which a hybrid neural network combining a CNN and several ANNs are shown useful for predicting G-ONSR for Ps-256QAM raw data in deployed SSMF metro networks with 0.27 dB RMSE. As demonstrated, the CNN classifier is trained with 80.96% testing accuracy to identify channel shaping factor. Several ANN regression models are trained to estimate G-OSNR with 0.2 dB for channels with various constellation shaping. Further aspects include the tuning of existing optical networks and the characterization of retrofit/upgraded optical networks to estimate capacity—both aspects employing our inventive hybrid neural network methodology.


Find Patent Forward Citations

Loading…