Convolutional neural nets with hyperparameter optimization and feature importance for power system static security assessment

Ramirez Gonzalez, Miguel; Segundo Sevilla, Felix Rafael; Korba, Petr; Castellanos-Bustamante, Rafael

doi:10.1016/j.epsr.2022.108203

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-25290

Publication type:	Article in scientific journal
Type of review:	Peer review (publication)
Title:	Convolutional neural nets with hyperparameter optimization and feature importance for power system static security assessment
Authors:	Ramirez Gonzalez, Miguel Segundo Sevilla, Felix Rafael Korba, Petr Castellanos-Bustamante, Rafael
et. al:	No
DOI:	10.1016/j.epsr.2022.108203 10.21256/zhaw-25290
Published in:	Electric Power Systems Research
Volume(Issue):	211
Issue:	108203
Issue Date:	21-Jun-2022
Publisher / Ed. Institution:	Elsevier
ISSN:	0378-7796 1873-2046
Language:	English
Subjects:	Power system security assessment; Convolutional neural networks; Hyperparameter optimization; Feature importance; Machine learning
Subject (DDC):	006: Special computer methods 621.3: Electrical, communications, control engineering
Abstract:	Static security assessment (SSA) is fundamental in electrical network analysis. However, the growing complexity and variability of grid’s operating conditions can make it tedious, slow, computationally intensive, and limited or impractical for on-line applications when traditional approaches are considered. Since this may hinder the emerging analytical duties of system operators, data-driven alternatives are required for faster and sophisticated decision-making. Although different machine learning algorithms (MLAs) could be applied, Convolutional Neural Networks (CNNs) are one of the most powerful models used in many advanced technological developments due to their remarkable capability to identify meaningful patterns in challenging and complex data sets. According to this, a CNN based approach for fast SSA of power systems with N-1 contingency is presented in this paper. To contribute to the automation of model building and tuning, a settings-free strategy to optimize a set of hyperparameters is adopted. Besides, permutation feature importance is considered to identify only a subset of key features and reduce the initial input space. To illustrate the application of the proposed approach, the simulation model of a practical grid in Mexico is used. The superior performance of the CNN alternative is demonstrated by comparing it with two popular MLAs.
URI:	https://digitalcollection.zhaw.ch/handle/11475/25290
Fulltext version:	Published version
License (according to publishing contract):	CC BY 4.0: Attribution 4.0 International
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:

File	Description	Size	Format
2022_Ramirez-Gonzalez-etal_Convolutional-neural-nets-hyperparameter.pdf		2.39 MB	Adobe PDF	View/Open

Show full item record

Ramirez Gonzalez, M., Segundo Sevilla, F. R., Korba, P., & Castellanos-Bustamante, R. (2022). Convolutional neural nets with hyperparameter optimization and feature importance for power system static security assessment. Electric Power Systems Research, 211(108203). https://doi.org/10.1016/j.epsr.2022.108203

Ramirez Gonzalez, M. et al. (2022) ‘Convolutional neural nets with hyperparameter optimization and feature importance for power system static security assessment’, Electric Power Systems Research, 211(108203). Available at: https://doi.org/10.1016/j.epsr.2022.108203.

M. Ramirez Gonzalez, F. R. Segundo Sevilla, P. Korba, and R. Castellanos-Bustamante, “Convolutional neural nets with hyperparameter optimization and feature importance for power system static security assessment,” Electric Power Systems Research, vol. 211, no. 108203, Jun. 2022, doi: 10.1016/j.epsr.2022.108203.

RAMIREZ GONZALEZ, Miguel, Felix Rafael SEGUNDO SEVILLA, Petr KORBA und Rafael CASTELLANOS-BUSTAMANTE, 2022. Convolutional neural nets with hyperparameter optimization and feature importance for power system static security assessment. Electric Power Systems Research. 21 Juni 2022. Bd. 211, Nr. 108203. DOI 10.1016/j.epsr.2022.108203

Ramirez Gonzalez, Miguel, Felix Rafael Segundo Sevilla, Petr Korba, and Rafael Castellanos-Bustamante. 2022. “Convolutional Neural Nets with Hyperparameter Optimization and Feature Importance for Power System Static Security Assessment.” Electric Power Systems Research 211 (108203). https://doi.org/10.1016/j.epsr.2022.108203.

Ramirez Gonzalez, Miguel, et al. “Convolutional Neural Nets with Hyperparameter Optimization and Feature Importance for Power System Static Security Assessment.” Electric Power Systems Research, vol. 211, no. 108203, June 2022, https://doi.org/10.1016/j.epsr.2022.108203.