Small-signal stability assessment with transfer learning-based convolutional neural networks

Ramirez Gonzalez, Miguel; Nösberger, Lukas; Segundo Sevilla, Felix Rafael; Korba, Petr

doi:10.1109/EPEC56903.2022.9999738

Publication type:	Conference paper
Type of review:	Peer review (publication)
Title:	Small-signal stability assessment with transfer learning-based convolutional neural networks
Authors:	Ramirez Gonzalez, Miguel Nösberger, Lukas Segundo Sevilla, Felix Rafael Korba, Petr
et. al:	No
DOI:	10.1109/EPEC56903.2022.9999738
Proceedings:	2022 IEEE Electrical Power and Energy Conference (EPEC)
Page(s):	386
Pages to:	391
Conference details:	2022 IEEE Electrical Power and Energy Conference (EPEC), online, 5-7 December 2022
Issue Date:	7-Dec-2022
Publisher / Ed. Institution:	IEEE
ISBN:	978-1-6654-6318-8
ISSN:	2381-2842
Language:	English
Subjects:	Power system; Small-signal stability; Convolutional neural network; Transfer learning; Feature importance
Subject (DDC):	621.3: Electrical, communications, control engineering
Abstract:	An approach for the small-signal stability assessment (SSSA) of power systems using a Convolutional Neural Network (CNN) model with transfer learning is presented in this paper. The concept of permutation feature importance (PFI) is included in model development to identify and drop the most irrelevant features in a given dataset, which minimizes the input information required by the model to achieve a certain performance and reduces the set of measurement locations for the related application. Then, a transfer learning approach using weight initialization and feature extraction is applied to leverage the knowledge of a pretrained model when a new independent dataset (obtained from the integration of converter-interfaced generation) is considered. Simulation results demonstrate that the transfer learning-based CNN model is able to exploit previous knowledge and provide a superior performance, as compared to the traditional rebuilt-from-scratch model.
URI:	https://digitalcollection.zhaw.ch/handle/11475/26641
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Energy Systems and Fluid Engineering (IEFE)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

There are no files associated with this item.

Show full item record

Ramirez Gonzalez, M., Nösberger, L., Segundo Sevilla, F. R., & Korba, P. (2022). Small-signal stability assessment with transfer learning-based convolutional neural networks [Conference paper]. 2022 IEEE Electrical Power and Energy Conference (EPEC), 386–391. https://doi.org/10.1109/EPEC56903.2022.9999738

Ramirez Gonzalez, M. et al. (2022) ‘Small-signal stability assessment with transfer learning-based convolutional neural networks’, in 2022 IEEE Electrical Power and Energy Conference (EPEC). IEEE, pp. 386–391. Available at: https://doi.org/10.1109/EPEC56903.2022.9999738.

M. Ramirez Gonzalez, L. Nösberger, F. R. Segundo Sevilla, and P. Korba, “Small-signal stability assessment with transfer learning-based convolutional neural networks,” in 2022 IEEE Electrical Power and Energy Conference (EPEC), Dec. 2022, pp. 386–391. doi: 10.1109/EPEC56903.2022.9999738.

RAMIREZ GONZALEZ, Miguel, Lukas NÖSBERGER, Felix Rafael SEGUNDO SEVILLA und Petr KORBA, 2022. Small-signal stability assessment with transfer learning-based convolutional neural networks. In: 2022 IEEE Electrical Power and Energy Conference (EPEC). Conference paper. IEEE. 7 Dezember 2022. S. 386–391. ISBN 978-1-6654-6318-8

Ramirez Gonzalez, Miguel, Lukas Nösberger, Felix Rafael Segundo Sevilla, and Petr Korba. 2022. “Small-Signal Stability Assessment with Transfer Learning-Based Convolutional Neural Networks.” Conference paper. In 2022 IEEE Electrical Power and Energy Conference (EPEC), 386–91. IEEE. https://doi.org/10.1109/EPEC56903.2022.9999738.

Ramirez Gonzalez, Miguel, et al. “Small-Signal Stability Assessment with Transfer Learning-Based Convolutional Neural Networks.” 2022 IEEE Electrical Power and Energy Conference (EPEC), IEEE, 2022, pp. 386–91, https://doi.org/10.1109/EPEC56903.2022.9999738.