.png){kind=icon}
返回
Machine-learning-based EDFA gain estimation [Invited]
.png){kind=icon}
OA
AI
DOI：10.1364/JOCN.417584.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Optical transmission systems with high spectral efficiency require accurate quality of transmission estimation for optical channel provisioning. However, the wavelength-dependent gain effects of erbium-doped fiber amplifiers (EDFAs) complicate precise optical channel power prediction and low-margin operation. In this work, we examine supervised machine learning methods using multiple artificial neural networks (ANNs) to build models for gain spectra prediction of optical transmission line EDFAs under different operating conditions. Channell-oading configurations and channel input power spectra are used as an a posteriori knowledge data feature for model training. In a hybrid learning approach, estimated gain spectra calculated by an analytical model are added as an a priori input data feature to further improve the EDFA ANN model performance in terms of prediction accuracy, training time, and quantity of training data. Using these methods, the root mean square error and maximum absolute error of the predicted channel output power can be as low as 0.144 dB and 1.6 dB, respectively. (C) 2021 Optical Society of America
Keyword:
POWER EXCURSIONS
期刊
IF:
4.3
论文数:
2.3K
被引数:
3.8K
机构
引用论文
Modeling EDFA Gain Ripple and Filter Penalties With Machine Learning for Accurate QoT Estimation
OAAI
OAAI分享收藏An earwig (Insecta: Dermaptera) in Early Cretaceous amber from Spain西班牙早白垩纪琥珀中的蠼螋（Insecta: Dermaptera）
PREAI
分享收藏Introducing Load Aware Neural Networks for Accurate Predictions of Raman Amplifiers引入负载感知神经网络以准确预测拉曼放大器OAAI
OAAI分享收藏All-Optical Networking-Evolution, Benefits, Challenges, and Future Vision.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Dual-wavelength source based optical circuit switching and wavelength reconfiguration in multi-hop ROADM systemsOPTICS EXPRESSOAAI
OPTICS EXPRESSIF3.3
OAAI分享收藏
查看更多内容