Data-Driven Analysis of Electrical Infrastructure: Identifying Consumption Patterns and Irregularities in Minas Gerais - Brazil

EasyChair Preprint 15671

Abstract

In the current context, data science and system identification emerge as fundamental themes to optimize complex processes in several industrial sectors. This study proposes a data integration methodology to analyze and identify consumption patterns in the electrical infrastructure of a region in the state of Minas Gerais, using data from irregularity reports and network monitoring. Initially, the data were extracted and processed using Extraction, Transformation, and Loading (ETL) techniques, allowing a detailed understanding of consumption patterns and commercial losses over time. In addition, georeferenced data were used to map the areas with the highest incidence of reports and energy losses. The analysis revealed a direct association between areas with high commercial losses and occurrences of illegal connections. Regions with significant losses, especially above 30%, proved to be places with a higher incidence of irregularities. The integration of georeferenced data from the electrical grid infrastructure facilitated the visualization of these patterns, allowing the precise identification of areas with potential problems and the most compromised feeders. Furthermore, the behavior of feeders with high and low commercial losses over time was examined. In feeders with high losses, a greater disparity between the measurement and expected consumption was observed, suggesting the presence of irregularities in the energy distribution. On the other hand, in feeders with low losses, a proximity between the measurement and expected consumption curves was observed, indicating a more efficient operation of the power grid.

Keyphrases: Alimentadores, Ciência de dados, Dados georreferenciados, Denúncias procedentes, Identificação de Sistemas, Perdas Comerciais

@booklet{EasyChair:15671,
  author    = {Álisson de Oliveira Alves and Luiz Eduardo Nunes Cho Luck and Luisa Christina de Souza and Raniere Rodrigues Melo de Lima and Carlos Augusto Teixeira de Moura and Wesley José dos Santos Marinho and Rafael de Medeiros Mariz Capuano and Bruno Cesar Pereira da Costa and Marina de Siqueira and Arthur Diniz Flor Torquato Fernandes and Jesaias Carvalho Pereira Silva and Pablo Javier Alsina},
  title     = {Data-Driven Analysis of Electrical Infrastructure: Identifying Consumption Patterns and Irregularities in Minas Gerais - Brazil},
  howpublished = {EasyChair Preprint 15671},
  year      = {EasyChair, 2025}}