Non-Technical Losses Estimation: A Top-Down Approach

• Grant number: 23/03151-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2023
• End date: August 31, 2024
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Lucas Teles de Faria
• Grantee: Luiz Paulo Barbosa do Nascimento Filho
• Host Institution: Faculdade de Engenharia e Ciências (FEC). Universidade Estadual Paulista (UNESP). Campus de Rosana. Rosana , SP, Brazil
• Associated scholarship(s): 23/14980-9 - Comparative Analysis Among Soft Computing Techniques for Non-Technical Losses Detection in Power Distribution Systems, BE.EP.IC

Abstract

Non-technical losses or commercial losses caused by theft (illegal connections) and fraud in the energy meter cause significant financial losses to power utilities and society. Namely: damage to energy quality (with an increase in blackouts), damage to the power grid reliability (with undue changes in the network topology), an increase in the energy bill, reduction in tax collection and others. Most studies in the specialized literature apply techniques from soft computing to detect irregular consumer units. Namely: artificial neural networks, fuzzy inference systems, support vector machine and others. However, these techniques are unable to determine all irregular consumers. Thus, non-localized irregular consumers may be concentrated in certain city subareas. This produces urban segregation. In this context, this study proposes the development of a top-down methodology to combat and prevent non-technical losses. In the first step, the subareas vulnerable to losses are estimated via geographically Weighted Regression GWR - top step. In the next step, irregular consumer units are detected within of subareas vulnerable to non-technical losses via Fuzzy ARTMAP artificial neural network - down step. The proposal methodology results consist of loss probability maps with the estimation of areas vulnerable to non-technical losses and the detection of irregular consumer units within these subareas vulnerable to losses.