Regression Analysis Applied to Time-Series Data of Smart Meters for Identifying Energy Theft in Electric Power Distribution Systems

• Grant number: 25/00865-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2025
• End date: March 31, 2026
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Fernanda Caseño Trindade Arioli
• Grantee: Pedro Arrelaro Ribeiro
• Host Institution: Faculdade de Engenharia Elétrica e de Computação (FEEC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Managing energy losses is a constant concern for electrical energy distribution companies and society as a whole, as these losses affect the efficiency of electrical systems. Energy losses can be categorized into two types: technical and non-technical losses. Technical losses are inherent to the operation of the electrical system, such as those caused by the Joule effect. In contrast, non-technical losses arise from fraud, theft of electricity, or issues related to measurement and billing processes by distribution companies. A significant number of fraudulent users can lead to unexpected overloading of the system, resulting in additional costs for network expansion, operation, and maintenance. Given the need for effective management of non-technical losses in electrical energy distribution systems, this scientific initiation project aims to apply regression analysis for detecting energy theft using data obtained from smart meters and electrical network models. The project will focus on power flow simulations, data analysis, and statistical methods to identify fraudulent consumers.