Emergency Control of Interconnected Power Systems: Developing a Control Action Selection Method Based on Pattern Recognition

Modern power systems are faced with increasing uncertainty due to the integration of renewable energy and distributed generation. This complicates emergency control. Traditional methods are ineffective in non-design conditions. The goal of the study was to develop an intelligent control approach, including data preprocessing, neural network architecture analysis, and a metric for classification quality assessment. The novel approach combines clustering, visualization, and parameter filtration to extract informative features from data. CNN, GAN, and ViT were analyzed for classifying states of electrical power systems. The method includes mode modelling, dimensionality reduction, clustering, feature selection, and dynamic testing. The model’s stability was confirmed when full topological data was available. Results show the possibility of decision-making in milliseconds, important for accident prevention. Future work includes expanding the training domain, analyzing transient processes, integrating real-time telemetry, and creating a fully controlled emergency control system using machine learning.

Authors

Institutions

Publication Details

Journal
Mathematics
Published
2026-11-16
DOI
https://doi.org/10.3390/math14224201
Primary Topic
Power System Optimization and Stability
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Emergency Control of Interconnected Power Systems: Developing a Control Action Selection Method Based on Pattern Recognition

Murodbek Safaraliev, Vladislav V. Popovtsev, Mihail D. Senyuk
Mathematics
Power System Optimization and Stability
article

Emergency Control of Interconnected Power Systems: Developing a Control Action Selection Method Based on Pattern Recognition

Murodbek Safaraliev, Vladislav V. Popovtsev, Mihail D. Senyuk
article en

Abstract

Modern power systems are faced with increasing uncertainty due to the integration of renewable energy and distributed generation. This complicates emergency control. Traditional methods are ineffective in non-design conditions. The goal of the study was to develop an intelligent control approach, including data preprocessing, neural network architecture analysis, and a metric for classification quality assessment. The novel approach combines clustering, visualization, and parameter filtration to extract informative features from data. CNN, GAN, and ViT were analyzed for classifying states of electrical power systems. The method includes mode modelling, dimensionality reduction, clustering, feature selection, and dynamic testing. The model’s stability was confirmed when full topological data was available. Results show the possibility of decision-making in milliseconds, important for accident prevention. Future work includes expanding the training domain, analyzing transient processes, integrating real-time telemetry, and creating a fully controlled emergency control system using machine learning.

MathematicsVol. 14(22)
Ural Federal University (RU), Technological University of Tajikistan (TJ), Tajik Technical University named after academic M.S.Osimi (TJ)
Industry, innovation and infrastructure, Affordable and clean energy
Power System Optimization and Stability
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon