Neural Network Design for Impedance Modeling of Power Electronic Systems Based on Latent Features

Data-driven approaches are promising to address the modeling issues of modern power electronics-based power systems, due to the black-box feature. Frequency-domain analysis has been applied to address the emerging small-signal oscillation issues caused by converter control interactions. However, the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transaction on neural networks and learning systems 2024-05, Vol.35 (5), p.5968-5980
Main Authors: Liao, Yicheng, Li, Yufei, Chen, Minjie, Nordstrom, Lars, Wang, Xiongfei, Mittal, Prateek, Poor, H. Vincent
Format: Article
Language:English
Subjects:
Analytical models
Artificial neural networks
Clustering
Computation
Data models
Deep learning
Electronic systems
Frequency domain analysis
frequency-domain model
Impedance
Industrial applications
latent features
Modelling
multilayer perceptron
Multilayers
Network design
Neural networks
Power electronics
Power system stability
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Data-driven approaches are promising to address the modeling issues of modern power electronics-based power systems, due to the black-box feature. Frequency-domain analysis has been applied to address the emerging small-signal oscillation issues caused by converter control interactions. However, the frequency-domain model of a power electronic system is linearized around a specific operating condition. It thus requires measurement or identification of frequency-domain models repeatedly at many operating points (OPs) due to the wide operation range of the power systems, which brings significant computation and data burden. This article addresses this challenge by developing a deep learning approach using multilayer feedforward neural networks (FNNs) to train the frequency-domain impedance model of power electronic systems that is continuous of OP. Distinguished from the prior neural network designs relying on trial-and-error and sufficient data size, this article proposes to design the FNN based on latent features of power electronic systems, i.e., the number of system poles and zeros. To further investigate the impacts of data quantity and quality, learning procedures from a small dataset are developed, and K-medoids clustering based on dynamic time warping is used to reveal insights into multivariable sensitivity, which helps improve the data quality. The proposed approaches for the FNN design and learning have been proven simple, effective, and optimal based on case studies on a power electronic converter, and future prospects in its industrial applications are also discussed.
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2023.3235806