Rocío Millán

MIDAS: detection of non-technical losses in electrical consumption using neural networks and statistical techniques

Datamining has become increasingly common in both the public and private sectors. 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. The detection of non-technical losses (which includes fraud detection) is a field where datamining has been applied successfully in recent times. However, the research in electrical companies is still limited, making it quite a new research topic. This paper describes a prototype for the detection of non-technical losses by means of two datamining techniques: neural networks and statistical studies. The methodologies developed were applied to two customer sets in Seville (Spain): a little town in the south (pop: 47,000) and hostelry sector. The results obtained were promising since new non-technical losses (verified by means of in-situ inspections) were detected through both methodologies with a high success rate.

Integrated expert system applied to the analysis of non-technical losses in power utilities

The detection of non-technical losses (NTLs), in most papers, commonly deals with the utilization of the registered consumption for each customer; besides, some researchers used the economic activity, the active/reactive ratio and the contract power. Currently, utility company databases store enormous amounts of information on both installations and customers: consumption, technical information on the measure equipment, documentation, inspections results, commentaries of inspectors, etc. In this paper, an integrated expert system (IES) for the analysis and classification of all the available useful information of the customer is presented. Customer classification identifies the presence of an NTL and the problem type. This IES include several modules: text mining module for analysis of inspector commentaries and extraction of additional information on the customer, data mining module to draw up the rules that determine the customer estimate consumption, and the Rule Based Expert System module to analyze each customer using the results of the text and data mining modules. This IES is used with real data extracted from Endesa company databases. Endesa is the most important power distribution company in Spain, and one of the most significant companies of Europe. This IES is used in the test phase by human experts in the Endesa company. In this phase, the IES is used as a Decision Support System (DSS), as it contains another module which provides a report with additional information about the customer and a summarized result that the inspectors can use to reach a decision.

Variability and Trend-Based Generalized Rule Induction Model to NTL Detection in Power Companies

This paper proposes a comprehensive framework to detect non-technical losses (NTLs) and recover electrical energy (lost by abnormalities or fraud) by means of a data mining analysis, in the Spanish Power Electric Industry. It is divided into four section: data selection, data preprocessing, descriptive, and predictive data mining. The authors insist on the importance of the knowledge of the particular characteristics of the Power Company customer: the main features available in databases are described. The paper presents two innovative statistical estimators to attach importance to variability and trend analysis of electric consumption and offers a predictive model, based on the Generalized Rule Induction (GRI) model. This predictive analysis discovers association rules in the data and it is supplemented by a binary Quest tree classification method. The quality of this framework is illustrated by a case study considering a real database, supplied by Endesa Company.

A Mining Framework to Detect Non-technical Losses in Power Utilities.

This paper deals with the characterization of customers in power companies in order to detect consumption Non-Technical Losses (NTL). A new framework is presented, to find relevant knowledge about the particular characteristics of the electric power customers. The authors uses two innovative statistical estimators to weigh variability and trend of the customer consumption. The final classification model is presented by a rule set, based on discovering association rules in the data. The work is illustrated by a case study considering a real

Increasing the efficiency in Non-Technical Losses detection in utility companies

Usually, the fraud detection method in utility companies uses the consumption information, the economic activity, the geographic location, the active/reactive ration and the contracted power. This paper proposes a combined text mining and neural networks to increase the efficiency in Non-Technical Losses (NTLs) detection methods which was previously applied. This proposed framework proposes to collect all the information that normally cannot be treated with traditional methods. This framework is part of a research project. This project is done in collaboration with Endesa, one of the most important power distribution companies of Europe. Currently, the proposed framework is in the test stage and it uses real cases.

Using regression analysis to identify patterns of non-technical losses on power utilities

A non-technical loss (NTL) is defined as any consumed energy or service which is not billed because of measurement equipment failure or illintentioned and fraudulent manipulation of said equipment. This paper describes new advances that we have developed for Midas project. This project is being developed in the Electronic Technology Department of the University of Seville and its aim is to detect non-technical losses in the database of the Endesa Company. The main symptom of a NTL in a customer is an important drop in his billed energy. Thus, a main task for us is to detect customers with anomalous drops in their consumed energy. Concretely, in the paper we present two new algorithms based on a regression analysis in order to detect two types of patterns of decreasing consumption typical in customers with NTLs.

Non-Technical Losses Reduction by Improving the Inspections Accuracy in a Power Utility

The Endesa Company is the main power utility in Spain. One of the main concerns of power distribution companies is energy loss, both technical and non-technical. A non-technical loss (NTL) in power utilities is defined as any consumed energy or service that is not billed by some type of anomaly. The NTL reduction in Endesa is based on the detection and inspection of the customers that have null consumption during a certain period. The problem with this methodology is the low rate of success of these inspections. This paper presents a framework and methodology, developed as two coordinated modules, that improves this type of inspection. The first module is based on a customer filtering based on text mining and a complementary artificial neural network. The second module, developed from a data mining process, contains a Classification & Regression tree and a Self-Organizing Map neural network. With these modules, the success of the inspections is multiplied by 3. The proposed framework was developed as part of a collaboration project with Endesa.