A Grey-box Model for Estimating Nonlinear SNR in Optical Networks Based on Physics-guided Neural Networks

Xiaomin Liu; Lei Liu; Huazhi Lun; Yihao Zhang; Lilin Yi; Weisheng Hu; Qunbi Zhuge

doi:10.1364/acpc.2021.m5i.1

ScienceGate Book Chapters

JOURNAL ARTICLE

A Grey-box Model for Estimating Nonlinear SNR in Optical Networks Based on Physics-guided Neural Networks

Xiaomin Liu Lei Liu Huazhi Lun Yihao Zhang Lilin Yi Weisheng Hu Qunbi Zhuge

Year: 2021 Journal: Asia Communications and Photonics Conference 2021 Pages: M5I.1-M5I.1

DOI: 10.1364/acpc.2021.m5i.1

Get Full-Text PDF Get Analytical Report

Abstract

Based on physics-guided neural network, we design the features and loss function for estimating nonlinear SNR. With 1603 examples from simulations, a shallow neural network can have a higher accuracy and a better physical consistency.

Keywords:

Artificial neural network Nonlinear system Consistency (knowledge bases) Computer science Function (biology) Artificial intelligence Algorithm Physics

Metrics

Cited By

0.25

FWCI (Field Weighted Citation Impact)

Refs

0.52

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Neural Networks and Reservoir Computing

Physical Sciences → Computer Science → Artificial Intelligence

Optical Network Technologies

Physical Sciences → Engineering → Electrical and Electronic Engineering

Advanced Photonic Communication Systems

Physical Sciences → Engineering → Electrical and Electronic Engineering

A Grey-box Model for Estimating Nonlinear SNR in Optical Networks Based on Physics-guided Neural Networks

Abstract

Metrics

Citation History

Topics

Related Documents

Fusing Physics to Fiber Nonlinearity Model for Optical Networks Based on Physics-Guided Neural Networks

PHYGNN (Physics Guided Neural Networks)

Imperfect physics-guided neural networks

Predicting nonlinear optical scattering with physics-driven neural networks

Predicting nonlinear optical scattering with physics informed neural networks