Optimized Combat to Non-Technical Losses in Power Distribution Systems

• Grant number: 24/13452-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2024
• End date: September 30, 2025
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Lucas Teles de Faria
• Grantee: Isabela Mendes de Oliveira
• Host Institution: Faculdade de Engenharia e Ciências (FEC). Universidade Estadual Paulista (UNESP). Campus de Rosana. Rosana , SP, Brazil

Abstract

Non-technical or commercial losses are present in all power distribution systems and represent a challenge to power utilities. They result from illicit practices such as clandestine connections and fraud in energy meters. Non-technical losses have substantial financial impacts on power utilities and society, such as blackouts and damage to power quality and reliability. Most studies on non-technical losses apply efficient soft computing techniques to detect irregular consumer units; however, they do not consider the cost-benefit ratio, that is, the cost of field inspections and the financial return of these inspections (recovered energy). In this sense, this project aims to develop a methodology that consists of three steps: (i) detection of irregular consumer units based on the monthly consumption history in kWh, (ii) estimation of lost energy, and (iii) optimized flow for field inspections considering the minimization of cost-benefit ratio. The detection and estimation of lost energy will be performed using a multilayer perceptron neural network with a time-delay neural network (TDNN). Future consumption will be estimated based on previous consumption. If there is a significant difference between actual and estimated consumption, then the consumer unit will be added to a list of possibly irregular consumers. This list comprises the input data for a mathematical model to define an optimized inspection flow considering the cost of field inspections and the recovered energy.