Research Interests:
Technologies to support the development of smarter energy systems and increase the opportunities for home energy management have increased in recent years. Through the addition of sensing, communication and drive components, devices and... more
Technologies to support the development of smarter energy systems and increase the opportunities for home energy management have increased in recent years. Through the addition of sensing, communication and drive components, devices and home appliances become increasingly "smart" so that they can communicate with each other, transmit data to end users and facilitate remote operation and automation, for example during periods of peak demand. This has the potential to provide energy-related benefits to end-users and network operators. One of the key benefits of intelligent techniques is the potential to support power reductions and demand side management. Within this context, this work aims to propose a system architecture for recommend suggestions to smart homes inhabitants (according to different user profiles), aiming cost reduction and energy efficiency. The work also includes the implementation of a RESTFul mining web service, which is part of the proposed architecture. The web service is used to release data mining, classifying data over the proposed recommender system. Through the data model transmission known as JSON (JavaScript Object Notation), the web service receives data and automatically convert to JSON Instances structures, processing the same with the data mining algorithms.
Research Interests:
The smart grids bring several new possibilities due to the new technology's needed for implementation. However, it may not be clear to the consumer what benefits can be achieved because of this new reality, triggering considerable... more
The smart grids bring several new possibilities due to the new technology's needed for implementation. However, it may not be clear to the consumer what benefits can be achieved because of this new reality, triggering considerable rejection rates due to lack of knowledge and information. New products and services can leverage integration between consumers and utilities, enabling better levels of energy efficiency by both consumers and utilities, which is one of the main objectives of smart grids. In this context, this article proposes the use of techniques to predict energy consumption as a useful tool for consumers and directly related to energy efficiency. It presents the main techniques for forecasting and a case study demonstrating the feasibility of the proposed solution. As a result, the method used reached a small margin of error in the short-term forecast.
Research Interests:
Smart grids are becoming increasingly closer to consumers, especially residential consumers, bringing with them a wide range of possibilities. The level of information obtained on a smart grid will be much higher when compared to a... more
Smart grids are becoming increasingly closer to consumers, especially residential consumers, bringing with them a wide range of possibilities. The level of information obtained on a smart grid will be much higher when compared to a traditional network and at this point, more informed consumers tend to consume more efficiently, bringing benefits to themselves and to the system. An interesting fact for control within a residence is forecasting consumption, allowing the consumer to know in advance how much to consume up to a certain period. Artificial neural networks are one of several methods used to forecast time series, however, require a high volume of historical data for the training of the network, given that these may not be accessible or even exist. At this point, the objective of this work is to evaluate the use of load curves obtained through computational tools for the pre-training of artificial neural networks used in the consumption forecast. A tool is used to create random load curves according to the region and socioeconomic characteristics. The load curves are transformed into cumulative consumption curves and used as training vectors of the artificial neural network. The results of the tests were very promising, they showed that the pretraining with the virtual data makes possible the forecast of the time series even in the absence of real data for the training, showing that the methodology developed has great potential of application in works related to the forecast consumption.
Research Interests:
Este artigo consiste em um estudo analítico de curvas de carga residenciais, para verificar a viabilidade da adoção da tarifa branca, a qual considera os registros de consumo em intervalos fixos no tempo. A ideia é obter os perfis de... more
Este artigo consiste em um estudo analítico de curvas de carga residenciais, para verificar a viabilidade da adoção da tarifa branca, a qual considera os registros de consumo em intervalos fixos no tempo. A ideia é obter os perfis de consumo que mais se beneficiariam com a adesão a essa alternativa tarifária no atual contexto brasileiro. O objetivo é verificar, a partir da análise das curvas, características de vários perfis de consumo, se a adesão à tarifa branca traria benefícios aos usuários. Idealmente, os consumidores não deveriam alterar radicalmente seus hábitos de consumo para reduzir seus custos com energia elétrica. Por outro lado, o alinhamento mais adequado de perfis de consumo com tarifas também propícia melhor aproveitamento da capacidade instalada por parte da concessionária. A metodologia proposta consiste então em avaliar curvas de carga sintetizadas a partir de dados estatísticos e da definição de cronogramas de consumo pré-estabelecidos pela concessionária para a...
Electrical energy management is a basic necessity for a country development, currently becoming theme of discussion by Government and Regulatory Agencies that looks for best practices on energy efficiency. For Brazil, the energy... more
Electrical energy management is a basic necessity for a country development, currently becoming theme of discussion by Government and Regulatory Agencies that looks for best practices on energy efficiency. For Brazil, the energy efficiency programs look continuously for private and public investments on new procedures, standards and projects but the return of investment is not considered in order to maximize the energy savings. Based on that, a deeper analysis is carried out on two main Brazilian Programs (Procel and PEE), comparing investments year over year, energy savings and return of investments. Based on this analysis, it's possible to note that majority of resources is not applied on the best projects or projects that are aligned with economical aspects of region, but on social projects due to Government regulations that don't have high return of investment. A proposal of change for the currently Brazilian scenario is also proposed in order to maximize the energy saving.
Research Interests:
Large power transformers are essential assets of the electrical system. Unexpected departure from transformers due to unobserved failures causes significant financial, social, and environmental losses. Analysis of dissolved gases in the... more
Large power transformers are essential assets of the electrical system. Unexpected departure from transformers due to unobserved failures causes significant financial, social, and environmental losses. Analysis of dissolved gases in the oil and the use of analytical tools for diagnosing incipient transformer failures, widely employed by utilities, may present low assertiveness and/or misdiagnosis. On the other hand, the improvement of computational intelligence techniques, coupled with new measurement technologies, has increased confidence in the diagnostics produced. In this context, to eliminate or reduce errors in the fault classification process, statistical analysis is required to get additional information, assess and treat the presence of outliers in the available dissolved gas data set. Therefore, in order to reduce the deleterious effects of untimely and unpredictable interruptions of transformers, this paper proposes a methodology for eliminating outliers based on limit va...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Several approaches have been proposed according the concepts of smart grids and the smart home is one of them. A smart home can be defined as a system with network communication between all devices allowing the control, monitoring and... more
Several approaches have been proposed according the concepts of smart grids and the smart home is one of them. A smart home can be defined as a system with network communication between all devices allowing the control, monitoring and remote access of the management system, progressing in a generalized way of all loads for an individual way, through individual management of loads. The paper proposes a Heating, Ventilation and Air Conditioning (HVAC) management methodology to be included in the Supervisor Control and Data Acquisition House Intelligent Management (SHIM). SHIM is a simulation platform developed and implemented in the Knowledge Engineering and Decision Support Research Center (GECAD) to support the control and management of appliances of end consumers. The main goal of the presented work is to develop a HVAC management methodology consisting in a priority system that classifies the importance of the HVAC in each instant. The priority classification depends directly on the difference between the room temperature and the user desired temperature, in order to take measures to optimize consumption during events with power consumption limitations maintaining user comfort.
Research Interests:
ABSTRACT
Research Interests:
Research Interests:
ABSTRACT
Research Interests:
ABSTRACT In this paper we propose a fast and an accurate method for fault diagnosis in power transformers by means of Optimum-Path Forest (OPF) classifier. Since we applied Dissolved Gas Analysis (DGA), the samples have been labeled by... more
ABSTRACT In this paper we propose a fast and an accurate method for fault diagnosis in power transformers by means of Optimum-Path Forest (OPF) classifier. Since we applied Dissolved Gas Analysis (DGA), the samples have been labeled by IEEE/IEC standard, which was further analyzed by OPF and several other well known supervised pattern recognition techniques. The experiments have showed that OPF can achieve high recognition rates with low computational cost.
Research Interests:
ABSTRACT The need for high reliability and environmental concerns are making the underground networks the most appropriate choice of energy distribution. However, like any other system, underground distribution systems are not free of... more
ABSTRACT The need for high reliability and environmental concerns are making the underground networks the most appropriate choice of energy distribution. However, like any other system, underground distribution systems are not free of failures. In this context, this work presents an approach to study underground systems using computational tools by integrating the software PSCAD/EMTDC with artificial neural networks to assist fault location in power distribution systems. Targeted benefits include greater accuracy and reduced repair time. The results presented here shows the feasibility of the proposed approach.
Research Interests:
ABSTRACT