Abstract: A non-technical loss is defined as any consumed energy or service which is not billed because of measurement equipment failure or ill-intentioned and fraudulent manipulation of said equipment. This paper describes new approaches to the detection of these for electrical companies. Concretely two different methods are proposed: one based on the detection by means of a clustering process with decision trees and another one with a simple but effective algorithm that allows detecting the customers with drastic drops of consumption. The analysis and the obtained results correspond to real customers of Endesa Company (one of the most important electrical companies of Spain).
Authors: Iñigo Monedero, Félix Biscarri, Carlos León, Juan Ignacio Guerrero, Jesús Biscarri, Rocío Millán.
Paper in Artificial Intelligence and Soft Computing (International) in Palma de Mallorca, Spain at September, 2009.
Publication: IASTED INTERNATIONAL CONFERENCE ARTIFICIAL INTELLIGENCE AND APPLICATIONS.
ISBN: 0-88986-452-7
[gview file=”https://grupo.us.es/ustic150/wp-content/uploads/2011/02/683-045.pdf”]