Análise Estatística para Seleção dos Atributos que Caracterizam os Indicadores de Continuidade do Fornecimento de Energia Elétrica

Abstract

To assess the quality of service provided by distributors, the National Electric Energy Agency (ANEEL) establishes service continuity indicators and limits for these indicators. The methodology for defining the limits is constantly updated, aiming to make it consistent with the characteristics of the distributors. In this context, the present work aims to analyze the change in the criteria of the statistical analysis for the selection of the attributes that characterize the continuity indicators. The proposed analysis is based on the same procedures used by ANEEL to define the current model for the characterization of continuity indicators, however, different statistical techniques from those employed by ANEEL are used. To validate the proposed methodology, eight case studies were developed using the software SAS University Edition. It was found that, using Stepwise regression, the increase in the correlation limit tends to decrease the explanatory power and the number of variables in the models, however, it increases the partial explanatory power of each variable present in the models.