Vulnerability estimation to non-technical losses by areas via geographically weighted models

• Grant number: 21/00960-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2021
• End date: June 30, 2022
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: Lucas Teles de Faria
• Grantee: Christian Calandrin
• Host Institution: Universidade Estadual Paulista (UNESP). Campus de Rosana. Rosana , SP, Brazil

Abstract

The insertion of smart grids in the electricity distribution system contributes to combat of the non-technical losses or commercial losses. However, this technology is not widely available in underdeveloped countries (such as Brazil, for example); precisely in those with more losses. Therefore, the development of techniques to combat these losses in conventional energy distribution networks is necessary. Non-technical losses are commonly caused by clandestine connections and meter fraud. They cause financial losses for power utilities and generate damage to electric power quality and reduce of the power grid reliability. Almost all studies on non-technical losses use soft computing techniques to detect irregular consumer units. However, in addition to detecting losses, we can also assess why they occur. In this context, the study of the characteristics of the place where they occur can bring relevant information for a better understanding of the problem. To this end, this project adopts a new approach with a focus on incorporating the study of geographic space to the problem of non-technical losses. Geographically weighted regression is used to produce choropleth maps that present the estimate of which subareas of the city are most vulnerable to these losses. From this study it is possible to identify which characteristics of these subareas that favor the appearance and the proliferation of these losses. These maps are an easy-to-interpret tool and can be used in conjunction with conventional tools for detecting irregular consumer units as decision support systems to determine priority regions of the city to prevent and combat non-technical losses.