Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Senyuk et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: