2008
Authors
Leite da Silva, AML; de Resende, LC; da Fonseca Manso, LAD; Miranda, V;
Publication
2008 10TH INTERNATIONAL CONFERENCE ON PROBABILISTIC METHODS APPLIED TO POWER SYSTEMS
Abstract
This paper presents a new methodology for assessing both reliability and well-being indices for composite generation and transmission systems. Firstly, a transmission network reduction is applied to find an equivalent for assessing composite reliability for practical large power systems. After that, in order to classify the operating states, Artificial Neural Networks (ANNs) based on Group Method Data Handling (GMDH) techniques are used to capture the patterns of the operating states, during the beginning of the non-sequential Monte Carlo simulation (MCS). The idea is to provide the simulation process with an intelligent memory, based only on polynomial parameters, to speed up the evaluation of the operating states. For the conventional reliability assessment, the ANNs are used to classify the operating states into success and failure. However, for the well-being analysis, only success states are classified into healthy and marginal by the ANNs. The proposed methodology is applied to the IEEE Reliability Test System 1996 and to a configuration of the Brazilian South-Southeastern System.
2008
Authors
Bessa, R; Miranda, V; Gama, J;
Publication
2008 IEEE POWER & ENERGY SOCIETY GENERAL MEETING, VOLS 1-11
Abstract
This paper reports new results in adopting entropy concepts to the training of mappers such as neural networks to perform wind power prediction as a function of wind characteristics (mainly speed and direction) in wind parks connected to a power grid. It also addresses the differences relevant to power system operation between off-line and on-line training of neural networks. Real case examples are presented.
2008
Authors
Lima, SEU; Frazão, O; Araújo, FM; Ferreira, LA; Miranda, V; Santos, JL;
Publication
19th International Conference on Optical Fibre Sensors
Abstract
2008
Authors
Ramirez Rosado, IJ; Garcia Garridoa, E; Fernandez Jimenez, LA; Zorzano Santamaria, PJ; Monteiro, C; Miranda, V;
Publication
RENEWABLE ENERGY
Abstract
The integration in electric power networks of new renewable energy facilities is the final result of a complex planning process. One of the important objectives of this process is the selection of suitable geographical locations where such facilities can be built. This selection procedure can be a difficult task because of the initially opposing positions of the different agents involved in this procedure, such as, for example, investors, utilities, governmental agencies or social groups. The conflicting interest of the agents can delay or block the construction of new facilities. This paper presents a new decision support system, based on Geographic Information Systems, designed to overcome the problems posed by the agents and thus achieve a consensual selection of locations and overcome the problems deriving from their preliminary differing preferences. This paper presents the description of the decision support system, as well as the results obtained for two groups of agents useful for the selection of locations for the construction of new wind farms in La Rioja (Spain).
2008
Authors
Miranda, V;
Publication
Modern Heuristic Optimization Techniques
Abstract
2008
Authors
Soares, RPDO; Castro, ARG; De Oliveira, RCL; Miranda, V;
Publication
Proceedings - 10th Brazilian Symposium on Neural Networks, SBRN 2008
Abstract
In this paper, Artificial Neural Networks (ANN) are used to model an extraction process that uses a supercritical fluid as solvent which its pilot installation is located at the Institute of Experimental and Technological Biology - IBET in Oeiras - Lisbon - Portugal. A strategy is used to complement the experimental data collected in laboratory during extraction procedures of useful compositions for the pharmaceutical industry using Black Agglomerate Residues (BAR) originating from of the cork production as raw material. The strategy involves fitting of data obtained during an operation of extraction. Two neural models are presented: the neural model trained using a Mean Square Error (MSE) minimization algorithm and the neural model which the learning was based on the error entropy minimization. A comparison of the performance of the two models is presented. © 2008 IEEE.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.