Fast non-technical losses identification through Optimum-Path Forest

Fraud detection in energy systems by illegal consumers is the most actively pursued study in non-technical losses by electric power companies. Commonly used supervised pattern recognition techniques, such as Artificial Neural Networks and Support Vector Machines have been applied for automatic commercial frauds identification, however they suffer from slow convergence and high computational burden. We introduced here the Optimum-Path Forest classifier for a fast non-technical losses recognition, which has been demonstrated to be superior than neural networks and similar to Support Vector Machines, but much faster. Comparisons among these classifiers are also presented. © 2009 IEEE.

Electrical consumers data clustering through optimum-path forest

Non-technical losses identification has been paramount in the last decade. Since we have datasets with hundreds of legal and illegal profiles, one may have a method to group data into subprofiles in order to minimize the search for consumers that cause great frauds. In this context, a electric power company may be interested in to go deeper a specific profile of illegal consumer. In this paper, we introduce the Optimum-Path Forest (OPF) clustering technique to this task, and we evaluate the behavior of a dataset provided by a brazilian electric power company with different values of an OPF parameter. © 2011 IEEE.

Envolvimento dos usuários no processo de inovação por meio da web 2.0: um estudo de caso na indústria automobilística

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Smart Grid e Carros Elétricos - Influência da Carga de Carros Elétricos Sobre o Sistema Elétrico

The technologies are advancing at a pace so expressive that allow the increase of the power quality from generation until the distribution to end customers. This improvement has been made possible through the automation of the energy that follows to a better quality of the energy provided, a lower energy supply disruptions and a very short recovery time. The trend of today and the near future is the distributed energy generation. To keep the automated control of the chain, the presence of Smart Grids is needed and that will be the most efficient and economical way to manage the entire system. Within this theme, is going to be necessary analyze the electric cars that promise to promote a more sustainable transport because it doesn’t uses fossil fuels, and more healthy because it does not emit pollutants into the atmosphere. The popularization of this type of vehicle is estimated to happen in a few decades and the case study analyzing its influence on the demand of the electrical system is something that will be very important in the near future. This paper presents a study of the influence of the inclusion of charges refering to electric cars

Controle de velocidade e tração de rodas independentes para veículos elétricos

This work presents a proposal to replace thetraditional system of traction electric car that usesone electric motor and a mechanical differential, by two electric motors of lower power, controlled byelectronic control low cost. The proposed control isopen loop and uses the technique of Pulse WidthModulation (PWM), discrete and synchronizedaiming to reduce the generation of harmonics. The implementation of two smaller motor one on each wheel-drive distributes the weight of the vehicle, improving the heat exchange of the windings,beyond enable the power components supporting a current of 50% predicted for only one motor . The solution adopted for being open-loop, has a similar behavior to the mechanical differential, where theeffort imposed by the trajectory makes the velocity distribution between the wheels be appropriate tovehicle trajectory

Electric load forecasting using a fuzzy ART&ARTMAP neural network

This work presents a neural network based on the ART architecture ( adaptive resonance theory), named fuzzy ART& ARTMAP neural network, applied to the electric load-forecasting problem. The neural networks based on the ARTarchitecture have two fundamental characteristics that are extremely important for the network performance ( stability and plasticity), which allow the implementation of continuous training. The fuzzy ART& ARTMAP neural network aims to reduce the imprecision of the forecasting results by a mechanism that separate the analog and binary data, processing them separately. Therefore, this represents a reduction on the processing time and improved quality of the results, when compared to the Back-Propagation neural network, and better to the classical forecasting techniques (ARIMA of Box and Jenkins methods). Finished the training, the fuzzy ART& ARTMAP neural network is capable to forecast electrical loads 24 h in advance. To validate the methodology, data from a Brazilian electric company is used. (C) 2004 Elsevier B.V. All rights reserved.

Suppression of Anderson localization of light in one-dimensional disordered photonic superlattices

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

A fast electric load forecasting using neural networks

The objective of this work is the development of a methodology for electric load forecasting based on a neural network. Here, it is used Backpropagation algorithm with an adaptive process based on fuzzy logic. This methodology results in fast training, when compared to the conventional formulation of Backpropagation algorithm. Results are presented using data from a Brazilian Electric Company and the performance is very good for the proposal objective.

A fast electric load forecasting using adaptive neural networks

This work presents a procedure for electric load forecasting based on adaptive multilayer feedforward neural networks trained by the Backpropagation algorithm. The neural network architecture is formulated by two parameters, the scaling and translation of the postsynaptic functions at each node, and the use of the gradient-descendent method for the adjustment in an iterative way. Besides, the neural network also uses an adaptive process based on fuzzy logic to adjust the network training rate. This methodology provides an efficient modification of the neural network that results in faster convergence and more precise results, in comparison to the conventional formulation Backpropagation algorithm. The adapting of the training rate is effectuated using the information of the global error and global error variation. After finishing the training, the neural network is capable to forecast the electric load of 24 hours ahead. To illustrate the proposed methodology it is used data from a Brazilian Electric Company. © 2003 IEEE.

Low-cost PWM speed controller for an electric mini-baja type vehicle

This paperwork presents a Pulse Width Modulation (PWM) speed controller for an electric mini-baja-type car. A battery-fed 1-kW three-phase induction motor provides the electric vehicle traction. The open-loop speed control is implemented with an equal voltage/frequency ratio, in order to maintain a constant amount of torque on all velocities. The PWM is implemented by a low-cost 8-bit microcontroller provided with optimized ROM charts for distinct speed value implementations, synchronized transition between different charts and reduced odd harmonics generation. This technique was implemented using a single passenger mini-baja vehicle, and the essays have shown that its application resulted on reduced current consumption, besides eliminating mechanical parts. Copyright © 2007 by ABCM.