Optical networks satisfy high bandwidth and low latency requirements for telecommunication networks and data center interconnection. To improve network resource utilization, machine learning (ML) is used to accurately model optical amplifiers such as erbium-doped fiber amplifiers (EDFAs), which impact end-to-end system performance such as quality of transmission. However, a comprehensive measurement dataset is required for ML to accurately predict an EDFA’s wavelength-dependent gain. We present an open dataset consisting of 202,752 gain spectrum measurements collected from 16 commercial-grade reconfigurable optical add–drop multiplexer (ROADM) booster and pre-amplifier EDFAs under varying gain settings and diverse channel-loading configurations over 2,785 hours in total, with a total dataset size of 3.1 GB. With this EDFA dataset, we implemented component-level deep-neural-network-based EDFA models and use transfer learning (TL) to transfer the EDFA model among 16 ROADM EDFAs, which achieve less than 0.18/0.24 dB mean absolute error for booster/pre-amplifier gain prediction using only 0.5% of the full target training set. We also showed that TL reduces the EDFA data collection requirements on a new gain setting or a different type of EDFA on the same ROADM.
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. Channel-loading 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.
more » « less- NSF-PAR ID:
- 10369595
- Publisher / Repository:
- Optical Society of America
- Date Published:
- Journal Name:
- Journal of Optical Communications and Networking
- Volume:
- 13
- Issue:
- 4
- ISSN:
- 1943-0620; JOCNBB
- Page Range / eLocation ID:
- Article No. B83
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
We measure the performance of separately characterized machine learning-based EDFA models for predicting the optical power spectrum evolution in a 5-span system with six ROADM nodes deployed in the COSMOS testbed, which achieve a mean absolute error of 0.6–0.7 dB after 10 EDFAs under varying channel loading configurations.more » « less
-
more » « less
Abstract Deep learning methods hold strong promise for identifying biomarkers for clinical application. However, current approaches for psychiatric classification or prediction do not allow direct interpretation of original features. In the present study, we introduce a sparse deep neural network (DNN) approach to identify sparse and interpretable features for schizophrenia (SZ) case–control classification. An
L 0‐norm regularization is implemented on the input layer of the network for sparse feature selection, which can later be interpreted based on importance weights. We applied the proposed approach on a large multi‐study cohort with gray matter volume (GMV) and single nucleotide polymorphism (SNP) data for SZ classification. A total of 634 individuals served as training samples, and the classification model was evaluated for generalizability on three independent datasets of different scanning protocols (N = 394, 255, and 160, respectively). We examined the classification power of pure GMV features, as well as combined GMV and SNP features. Empirical experiments demonstrated that sparse DNN slightly outperformed independent component analysis + support vector machine (ICA + SVM) framework, and more effectively fused GMV and SNP features for SZ discrimination, with an average error rate of 28.98% on external data. The importance weights suggested that the DNN model prioritized to select frontal and superior temporal gyrus for SZ classification with high sparsity, with parietal regions further included with lower sparsity, echoing previous literature. The results validate the application of the proposed approach to SZ classification, and promise extended utility on other data modalities and traits which ultimately may result in clinically useful tools.
