Abstract
This paper deals with a problem of identification of the best subset of variables that should be used for dynamic security assessment of a power system, when this task is pro-vided by artificial neural networks (ANN)- The approach de-scribed here exploits ANN output sensitivities relatively to the inputs and correlation degrees, to identify the most relevant system variables to be used for an effective security assessment task. The ANNs are initially trained with all low-correlated candidate features, which enables the sensitivity analyses for the initial set of system features. Derivatives of the ANN output relatively to each input are obtained by exploiting the chain rule, similar to the one used for weights adaptation on Back-propagation Algorithm. A description of the application of this approach in a real system is present in the paper. Results obtained in the dynamic security assessment problem of the network of the island of Crete were quite successful. © 2001 IEEE.

Abstract
Voltage stability has been of the major concern in power system operation. To prevent these problems, technical staff evaluates frequently the distance of the operation state to the voltage collapse point. This distance normally is calculated with power flow equations. This classic technique is very slow for electric power systems with large dimension. In abnormal exploration situations it may introduce serious limitation in the voltage stability analysis process. So, the application of a fast and reliable evaluation technique is very important to diminish the evaluation time. This paper presents a study of the application of artificial neural network (ANN) to the evaluation of this distance to the voltage collapse point. To detection the point of collapse the new method FSQV was used.

Abstract
Feature subset selection is a central issue in a vast diversity of problems including classification, function approximation, machine learning and adaptive control. On a wide variety of applications, especially when using real data, input features may be not independent and output variable depends on the relationship among inputs rather than on input values themselves. Feature selection methods that assume independence of attributes will fail on these cases. On the other side, most of alternative approaches are quasi-exhaustive, requiring large CPU processing time. In this paper, an alternative methodology based on sensitivity analysis of trained artificial neural networks (ANN) is analyzed. Results so far attained on illustrative toy examples and on real data support the validity of the developed approach.

Abstract
Pitch control has so far been the dominating method for power control in modern variable speed wind turbines. This paper proposes an improved control technique for pitching the blades of a variable speed wind turbine, using Artificial Neural Networks (ANN). The control objective is decided according the two states of operation: below rated operation and above rated operation. In the below rated power state, the aim of control is to extract maximum energy from the wind. In the above rated power, the control design problem is to limit and smooth the output electrical power. A model has been constructed and evaluated with experimental data obtained from Vestas V-47 660 kW wind turbine.

Abstract
The paper describes the on-line dynamic security assessment functions developed within the European Union, DGXII programme, CARE. These functions are based exclusively on the application of machine learning techniques. A description of the problem and the data set generation procedure for the Crete island power system are included. Comparative results regarding performances of Decision Trees, Kernel Regression Trees and Neural Networks are presented and discussed.The paper describes the on-line dynamic security assessment functions developed within the European Union, DGXII programme, CARE. These functions are based exclusively on the application of machine learning techniques. A description of the problem and the data set generation procedure for the Crete island power system are included. Comparative results regarding performances of Decision Trees, Kernel Regression Trees and Neural Networks are presented and discussed.

Abstract
Loads estimation is becoming each time more fundamental for an efficient management and planning of electric distribution systems. Among the factors that contribute to this need of more efficiency are the increasing complexity of these networks, the deregulation process and the competition in an open energy market, and environment preservation requirements. However, the only information generally available at MV and LV levels is essentially of commercial nature, i.e., monthly energy consumption, hired power contracts and activity codes. In consequence, distribution utilities face the problem of estimating load diagrams to be used in planning and operation studies. The typical procedure uses measurements in typical classes of consumers defined by experts to construct inference engines that, most of the times, only estimate peak loads. In this paper, the definition of classes was performed by clustering the collected load diagrams. Artificial Neural Networks (ANN) were then used for load Curve estimation. This article describes the adopted methodology and presents some representative results. Performance attained is discussed as well as a method to achieve confidence intervals of the main predicted diagrams.