Transient Stability Analysis Using the Concept of Inertia and Data Mining.
Gespeichert in:
| Titel: | Transient Stability Analysis Using the Concept of Inertia and Data Mining. (English) |
|---|---|
| Alternate Title: | Análisis de Estabilidad Transitoria Utilizando el Concepto de Inercia y Minería de Datos. (Spanish) |
| Autoren: | Noroña, N. R., Cajas, E. J., Chamba, M. S., Lozada, C. X. |
| Quelle: | Revista Técnica Energía; jul2025, Vol. 22 Issue 1, p1-11, 11p |
| Schlagwörter: | ELECTRIC power systems, DYNAMIC stability, TIME series analysis, DATA mining, ELECTRIC power engineering, MOMENTS of inertia, INERTIA (Mechanics) |
| Abstract (English): | This work proposes a methodology for evaluating transient stability in power systems using the time series clustering algorithm TimeSeriesKMeans, based on the Dynamic Time Warping (DTW) metric. A custom Python script is developed and integrated with DIgSILENT PowerFactory, allowing the extraction of rotor angles from each generator based on simulations carried out on the 39-bus, 10-generator New England test system. These angles are referenced to the Center of Inertia (COI), and the Python environment is used to apply the unwrapping technique, which corrects abrupt phase signal changes by eliminating discontinuities in the range from -p to p. Subsequently, the TimeSeriesKMeans algorithm with DTW is employed to cluster the generating units according to their transient response, enabling the identification of critical and non-critical units. Since DIgSILENT PowerFactory only allows the visualization of rotor angles relative to a single reference machine, this restricts the ability to fully observe the system's dynamic behavior. To overcome this limitation, the results obtained through the proposed methodology are implemented directly within DIgSILENT PowerFactory. The processed outputs, generated in Python, are then visualized within the DIgSILENT environment, contributing to more efficient decision-making in the operation and planning of Power Systems (PS). [ABSTRACT FROM AUTHOR] |
| Abstract (Spanish): | Este trabajo propone una metodología para evaluar la estabilidad transitoria en sistemas eléctricos de potencia mediante el algoritmo clustering de series temporales (TimeSeriesKMeans) utilizando la métrica Dynamic Time Warping (DTW). Se desarrolla un código mediante el lenguaje de programación Python integrado con DIgSILENT Power Factory, el cual permite extraer los ángulos del rotor de cada uno de los generadores basado en simulaciones en el sistema de New England de 39 barras y 10 generadores y referenciarlos al Centro de Inercia (COI, Center Of Inertia) y con el uso de Python aplicar la técnica de "unwrapping" que es una técnica que corrige los cambios bruscos de las señales de fase, eliminando así las discontinuidades existentes entre el rango de - p a p. Posteriormente, se emplea el algoritmo TimeSeriesKMeans basado en DTW para segmentar las unidades de generación según su respuesta transitoria, permitiendo identificar unidades críticas y no críticas. Dado a que DIgSILENT Power Factory solo permite representar los ángulos del rotor con respecto a una unidad de referencia, se limita del comportamiento del sistema. Para abordar esta limitación, se implementan los resultados de este trabajo directamente en DIgSILENT Power Factory, cuyas gráficas de resultados se procesan en Python y desplegadas en el entorno de DIgSILENT Power Factory, lo que contribuye a la toma de decisiones más eficientes en la operación y planificación del Sistemas Eléctricos de Potencia (SEP). [ABSTRACT FROM AUTHOR] |
| Copyright of Revista Técnica Energía is the property of Centro Nacional de Control de Energia CENACE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Datenbank: | Complementary Index |
Nájsť tento článok vo Web of Science Schreiben Sie den ersten Kommentar!