Metodologia de auxílio na tomada de decisão na formação de conjuntos de unidades consumidoras de energia elétrica

Abstract

The issue of Proceedings of Electric Power Distribution (PRODIST) confirmed the comparative analysis of the distribution companies of electricity established by Resolution 024/2000 as the basis for establishing the goals of continuity indicators DEC (Costomer Average Duration Interruption Index) and FEC (Costomer Average Frequency Interruption Index). The setting of targets is directly influenced by the definition of the sets of consumer units of the distribution companies of electricity is therefore of interest to the distribution companies a good definition of these sets. This work presents the development of a methodology based on machine learning techniques to assist companies in electric power distribution in decision making of the definition of sets of consumers units aimed at improving compatibility of the goals for the indications of DEC and FEC with reality assemblies in relation to environmental characteristics and of infrastructure of the concession area of the distribution company.