Análise dos Impactos Harmônicos na Qualidade da Energia Elétrica Utilizando KDD – Estudo de Caso na Universidade Federal do Pará

Abstract

This work presents an analysis of data related to Power Quality (PQ), focusing on the significant increase in harmonic distortion levels of current and voltage due to the growing use of non-linear loads and power electronics-based equipment. A methodology was developed using computational intelligence (CI) and data mining techniques to analyze data collected by power quality meters installed at the Federal University of Pará (UFPA). The KDD process was applied, including collection, selection, cleaning, integration, transformation, reduction, mining, interpretation, and evaluation of the data. The Naive Bayes classifier was used in the data mining phase, and the results demonstrated the applicability of the KDD process in the analysis of Total Harmonic Distortion of Voltage at the Common Coupling Point, which can be applied in commercial, residential, and industrial areas.