Juan I. Guerrero

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.

Rule-based system to detect energy efficiency anomalies in smart buildings, a data mining approach

Automatic system to detect energy efficiency anomalies in smart buildings.Definition and testing of energy efficiency indicators to quantify energy savings.Knowledge extraction from data and HVAC experts through Data Mining techniques.In this study a full set of anomalous EE consumption patterns are detected.During test period more than 10% of day presented a kind of EE anomaly. The rapidly growing world energy use already has concerns over the exhaustion of energy resources and heavy environmental impacts. As a result of these concerns, a trend of green and smart cities has been increasing. To respond to this increasing trend of smart cities with buildings every time more complex, in this paper we have proposed a new method to solve energy inefficiencies detection problem in smart buildings. This solution is based on a rule-based system developed through data mining techniques and applying the knowledge of energy efficiency experts. A set of useful energy efficiency indicators is also proposed to detect anomalies. The data mining system is developed through the knowledge extracted by a full set of building sensors. So, the results of this process provide a set of rules that are used as a part of a decision support system for the optimisation of energy consumption and the detection of anomalies in smart buildings.

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.

Decision system based on neural networks to optimize the energy efficiency of a petrochemical plant

Highlights? We developed a decision system to optimize the energy efficiency of a petrochemical plant. ? The decision system has been developed through a data mining process. ? The decision system is based on an algorithm and a kernel of neural networks. ? We have tested the system and obtained a save of 7%. ? The system has been integrated in a pilot software. The energy efficiency of industrial plants is an important issue in any type of business but particularly in the chemical industry. Not only is it important in order to reduce costs, but also it is necessary even more as a means of reducing the amount of fuel that gets wasted, thereby improving productivity, ensuring better product quality, and generally increasing profits. This article describes a decision system developed for optimizing the energy efficiency of a petrochemical plant. The system has been developed after a data mining process of the parameters registered in the past. The designed system carries out an optimization process of the energy efficiency of the plant based on a combined algorithm that uses the following for obtaining a solution: On the one hand, the energy efficiency of the operation points occurred in the past and, on the other hand, a module of two neural networks to obtain new interpolated operation points. Besides, the work includes a previous discriminant analysis of the variables of the plant in order to select the parameters most important in the plant and to study the behavior of the energy efficiency index. This study also helped ensure an optimal training of the neural networks. The robustness of the system as well as its satisfactory results in the testing process (an average rise in the energy efficiency of around 7%, reaching, in some cases, up to 45%) have encouraged a consulting company (ALIATIS) to implement and to integrate the decision system as a pilot software in an SCADA.

Improving Knowledge-Based Systems with statistical techniques, text mining, and neural networks for non-technical loss detection

Currently, power distribution companies have several problems that are related to energy losses. For example, the energy used might not be billed due to illegal manipulation or a breakdown in the customers measurement equipment. These types of losses are called non-technical losses (NTLs), and these losses are usually greater than the losses that are due to the distribution infrastructure (technical losses). Traditionally, a large number of studies have used data mining to detect NTLs, but to the best of our knowledge, there are no studies that involve the use of a Knowledge-Based System (KBS) that is created based on the knowledge and expertise of the inspectors. In the present study, a KBS was built that is based on the knowledge and expertise of the inspectors and that uses text mining, neural networks, and statistical techniques for the detection of NTLs. Text mining, neural networks, and statistical techniques were used to extract information from samples, and this information was translated into rules, which were joined to the rules that were generated by the knowledge of the inspectors. This system was tested with real samples that were extracted from Endesa databases. Endesa is one of the most important distribution companies in Spain, and it plays an important role in international markets in both Europe and South America, having more than 73 million customers.

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.

Heterogeneous data source integration for smart grid ecosystems based on metadata mining

A new technique based on metadata is proposed: metadata mining.An intelligent integration system for heterogeneous data sources is described.An adaptive data mining tool for the integrated data sources is proposed.Successful results are obtained in application in real data bases from research projects. The arrival of new technologies related to smart grids and the resulting ecosystem of applications and management systems pose many new problems. The databases of the traditional grid and the various initiatives related to new technologies have given rise to many different management systems with several formats and different architectures. A heterogeneous data source integration system is necessary to update these systems for the new smart grid reality. Additionally, it is necessary to take advantage of the information smart grids provide. In this paper, the authors propose a heterogeneous data source integration based on IEC standards and metadata mining. Additionally, an automatic data mining framework is applied to model the integrated information.

An Approach to Detection of Tampering in Water Meters

Abstract Meter tampering is defined as a fraudulent manipulation which implies a service that is not billed by a utility company. It is a lack of consumption control for the utility company and a main problem because they represent an important loss of income. We have developed a methodology consists of a set of three algorithms for the detection of meter tampering in the Emasesa Company (a water distribution company in Seville and one of the most important of the country). The algorithms were generated and programmed after a data mining process from the database of the company and they detect three type of consumption patterns: Progressive drops, sudden drops and abnormally low consumption. The methodology has been tested with in situ inspections of the customers of a village of the province of Seville. Once carried out the inspections by the utility, the inspectors confirmed a good success rate taking into account that the detection of this type of fraud is very difficult because it is a non-invasive technique. Besides, this type of detections is a topic that, if we take a look at the state of the art, there are few references or works.