Estimação da Margem de Carga de Potência Ativa Considerando Ruídos Não-Gaussianos

Abstract

This research aims to present an innovative approach to solving the problem of determining the active power load margin (PLM), considering variations in load bars, contingency situations and the application of non-Gaussian noise in phasor measurement units (PMU). Four case studies were carried out for the IEEE 14 bus system, which has four generating units, in order to demonstrate the applicability of the method in relation to the classical method of continuous power flow (CPF) calculation and in relation to the methodology based on neural networks present in the technical literature. The results obtained demonstrated that the computational effort of machine learning methods is generally lower than the CPF effort and the applicability of the Extremely Randomized Trees (ET) method for LPM calculation problems considering normal and contingency situations which presented the best results among the compared methods.