Analysis and Characterization of Power Quality using Data Mining
Article Sidebar
Main Article Content
Abstract
This work addresses the issue of power quality in electrical distribution networks, focusing on the identification and evaluation of harmonic distortions, which can affect equipment performance and regulatory compliance. To achieve this, a methodology was implemented that combines univariate analysis to verify compliance with the IEEE 519-2022 standard and the ARCONEL 009/2024 regulation, along with data mining techniques such as Principal Component Analysis (PCA) and the K-Means clustering algorithm, which classify harmonics based on their behavior within the electrical system. The methodology was validated through the analysis of historical harmonic data from a cement industry whose distribution network operates at 22 kV. The results made it possible to identify critical periods in which harmonic levels exceeded regulatory limits, mainly due to the operation of variable frequency drives, inverters, and rectifiers used in industrial processes such as raw material extraction, grinding, preheating, kiln operation, bagging, and dispatch. The developed model proved effective in processing large volumes of data, identifying the main sources of harmonic distortion, and segmenting behavior by time and day, thus facilitating the implementation of mitigation strategies and its adaptation to various industrial environments.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Aviso de Derechos de Autor
La Revista Técnica "energía" está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.
References
M. M. Irfan, M. Alharbi, y C. H. H. Basha, «Artificial neural network controlled DSTATCOM for mitigating power quality concerns in solar PV and wind system», Sci. Rep., vol. 15, n.o 1, 2025, doi: 10.1038/s41598-025-88540-0.
M. Pérez Martínez et al., «Desarrollo de aplicaciones en el software Scilab para el análisis de armónicos en sistemas industriales», Ing. Energética, vol. 43, n.o 1, pp. 24-34, abr. 2022.
L. Amaya-Vásquez, E. Inga-Ortega, L. Amaya-Vásquez, y E. Inga-Ortega, «Localización de Distorsiones Armónicas en Sistemas Eléctricos usando Sensado Comprimido», Ing. Compet., vol. 24, n.o 1, jun. 2022, doi: 10.25100/iyc.24i1.11037.
«IEEE Std 519-2022 (Revision of IEEE Std 519-2014)», IEEE Std 519-2022 Revis. IEEE Std 519-2014, pp. 1-31, ago. 2022, doi: 10.1109/IEEESTD.2022.9848440.
ARCONEL, Resolución Nro. ARCONEL-016/2024. 2024. [En línea]. Disponible en: https://controlelectrico.gob.ec/wp-content/uploads/downloads/2024/10/Regulacion-ARCONEL-006-24-1-3.pdf
J. C. Gonzales Arispe y A. Y. Marca Yucra, «Análisis de armónicos en sistemas eléctricos de potencia y normas regulatorias: impacto del horno de arco eléctrico de acerías», Ingeniare Rev. Chil. Ing., vol. 32, pp. 0-0, 2024, doi: 10.4067/s0718-33052024000100201.
S. S. Cembranel, F. Lezama, J. Soares, S. Ramos, A. Gomes, y Z. Vale, «A Short Review on Data Mining Techniques for Electricity Customers Characterization», en 2019 IEEE PES GTD Grand International Conference and Exposition Asia (GTD Asia), mar. 2019, pp. 194-199. doi: 10.1109/GTDAsia.2019.8715891.
B. L. Tarcsay, Á. Bárkányi, T. Chován, y S. Németh, «A Dynamic Principal Component Analysis and Fréchet-Distance-Based Algorithm for Fault Detection and Isolation in Industrial Processes», Processes, vol. 10, n.o 11, Art. n.o 11, nov. 2022, doi: 10.3390/pr10112409.
L. J. Lepolesa, S. Achari, y L. Cheng, «Electricity Theft Detection in Smart Grids Based on Deep Neural Network», IEEE Access, vol. 10, pp. 39638-39655, 2022, doi: 10.1109/ACCESS.2022.3166146.
J. Castro, P. Soto, R. Reategui, y T. Castillo, «Partición de una Red Eléctrica de Distribución Aplicando Algoritmos de Agrupamiento K-means y DBSCAN», Rev. Téc. Energ., vol. 20, n.o 1, Art. n.o 1, jul. 2023, doi: 10.37116/revistaenergia.v20.n1.2023.572.
L. Marrero et al., «Uso de algoritmo K-means para clasificar perfiles de clientes con datos de medidores inteligentes de consumo eléctrico: Un caso de estudio», Ingeniare Rev. Chil. Ing., vol. 29, n.o 4, pp. 778-787, dic. 2021, doi: 10.4067/S0718-33052021000400778.
C. Yajure, «Aplicación de la metodología de Ciencia de Datos para analizar datos de facturación de energía eléctrica. Caso de estudio: Uruguay 2000-2022», ResearchGate, doi: 10.15381/risi.v15i1.23544.
C. Yajure, «Uso de algoritmos de Machine Learning para analizar los datos de energía eléctrica facturada en la Ciudad de Buenos Aires durante el período 2010–2021», ResearchGate, oct. 2022, doi: 10.22206/cyap.2022.v5i2.pp7-37.
O. Yu. Maryasin y A. I. Lukashov, «A Python Application for Hourly Electricity Prices Forecasting Using Neural Networks», en 2020 International Russian Automation Conference (RusAutoCon), sep. 2020, pp. 138-143. doi: 10.1109/RusAutoCon49822.2020.9208035.
«Advanced Distribution Measurement Technologies and Data Applications for Smart Grids: A Review», ResearchGate, dic. 2024, doi: 10.3390/en13143730.
E. I. F. Cruz, «Análisis de Componentes Principales de la Tarifa de Electricidad en México – Caso de Estudio», Cienc. Lat. Rev. Científica Multidiscip., vol. 8, n.o 4, Art. n.o 4, sep. 2024, doi: 10.37811/cl_rcm.v8i4.13173.
D. Garcia-Alvarez y M. J. Fuente, «Estudio comparativo de técnicas de detección de fallos basadas en el Análisis de Componentes Principales (PCA)», Rev. Iberoam. Automática E Informática Ind. RIAI, vol. 8, n.o 3, pp. 182-195, jul. 2011, doi: 10.1016/j.riai.2011.06.006.
J. Zhuang, M. Dong, J. Lin, M. Liu, y K. Lin, «Electricity charge anomaly detection based on PCA-IK-means», en 2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications (ICPECA), ene. 2023, pp. 1714-1718. doi: 10.1109/ICPECA56706.2023.10076038.
E. Pérez-Montalvo et al., «Model of monthly electricity consumption of healthcare buildings based on climatological variables using PCA and linear regression», Energy Rep., vol. 8, pp. 250-258, nov. 2022, doi: 10.1016/j.egyr.2022.06.117.
J. Wang y X. Li, «Abnormal Electricity Detection of Users Based on Improved Canopy-Kmeans and Isolation Forest Algorithms», IEEE Access, vol. 12, pp. 99110-99121, 2024, doi: 10.1109/ACCESS.2024.3429304.
G. Ruiz Aranibar, «Análisis de conglomerados», Rev. Varianza, vol. 16, oct. 2019, Accedido: 10 de marzo de 2025. [En línea]. Disponible en: http://revistasbolivianas.umsa.bo/scielo.php?script=sci_abstract&pid=&lng=en&nrm=iso&tlng=
M. Dimishkieh y A. H. Ramzi, «An Enhanced k-Means Clustering Algorithm for Pattern Discovery in Healthcare Data», Sage J., jul. 2019, doi: https://doi.org/10.1155/2015/6157.
M. F. Abdullah, N. H. Hamid, Z. Baharudin, M. A. M. Ayob, y M. A. F. M. Hamim, «Characteristic of third harmonic from synchronous generator passing through transformer and rectifier», en 2012 IEEE International Conference on Power and Energy (PECon), dic. 2012, pp. 689-694. doi: 10.1109/PECon.2012.6450303.
A. R. Bonilla y H. T. Le, «Analysis and Mitigation of Harmonics for a Wastewater Treatment Plant Electrical System», WSEAS Trans. Circuits Syst., vol. 23, pp. 1-13, 2024, doi: 10.37394/23201.2024.23.1.
