Abstract
This paper presents an intelligent system for the detection of non-technical losses of electrical energy associated with the fraudulent behaviors of system users. This proposal has three stages: a non-supervised clustering of consumption profiles based on a hybrid algorithm between self-organizing maps (SOM) and genetic algorithms (GA). A second stage for demand forecasting is based on ARIMA (autoregressive integrated moving average) models corrected intelligently through neural networks (ANN). The final stage is a classifier based on random forests for fraudulent user detection. The proposed intelligent approach was trained and tested with real data from the Colombian Caribbean region, where the utility reports energy losses of around 18% of the total energy purchased by the company during the five last years. The results show an average overall performance of 82.9% in the detection process of fraudulent users, significantly increasing the effectiveness compared to the approaches (68%) previously applied by the utility in the region.
Highlights
As part of real-world processes, power systems are not capable of delivering all electrical power produced to users, so a difference between the energy generated and delivered is inherent to their operation
In the non-technical losses (NTL) group, we find products of errors and breakdowns in measurement equipment, energy not invoiced due to errors in meter reading or billing processes, and those associated with fraudulent behavior of customers, who evade payment corresponding to the consumption of electrical energy [4,5]
Itthat corresponds to the evaluation of the intelligent product of of computational techniques focus on characterizing aspects that are not system performance forsignificant the detection of analysis fraudulent users. energy consumption behaviors
Summary
As part of real-world processes, power systems are not capable of delivering all electrical power produced to users, so a difference between the energy generated and delivered is inherent to their operation. The impact of the problem is so severe that it is currently the focus of multiple worldwide research projects, which converge towards the use of algorithms and computational intelligence techniques [3] Such techniques facilitate the exploration, acquisition, processing, and analysis of large amounts of data, which any human being operator is not capable of, as well as a high degree of accuracy in the detection of fraud, which makes it possible to recover a large amount of the income [9,10]. The integration of clustering and forecasting techniques based on intelligent systems to identify fraudulent customers is a promising solution since the proposal allows to adapt and optimize the structure of the system for each customer In this sense, this approach differs from those presented in other works because it seeks to reinforce detection by including additional variables that are the results of other intelligent algorithms
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
