Sayed Ali Khaleghi - Mazandaran Regional Electric Company – Iran

This paper describes some new advances for the detection of non-technical losses in the customers of Mazandaran Electricity Distribution Company (MEDC). The advances presented in this article have an objective of detecting customers with anomalous drops in their consumed energy. Naïve Bayesian (NB) and decision tree (DT) classifiers have been used for detecting patterns of non-technical losses. We tested the performances of the DT and NB classifiers respectively using the classification accuracy, precision, sensitivity, specificity analysis, and ۱۰-fold cross validation on real datasets from MEDC. The proposed methods have been tested with real customers of the database of MEDC. The experiments carried out in the context of identifying non-technical losses in electricity distribution systems.

Data mining; Classification; Non-technical losses; Naïve Bayesian; Decision tree