Abstract
This paper presents a methodology supported on the data base knowledge discovery process (KDD), in order to find out the failure probability of electrical equipments', which belong to a real electrical high voltage network. Data Mining (DM) techniques are used to discover a set of outcome failure probability and, therefore, to extract knowledge concerning to the unavailability of the electrical equipments such us power transformers and high-voltages power lines. The framework includes several steps, following the analysis of the real data base, the pre-processing data, the application of DM algorithms, and finally, the interpretation of the discovered knowledge. To validate the proposed methodology, a case study which includes real databases is used. This data have a heavy uncertainty due to climate conditions for this reason it was used fuzzy logic to determine the set of the electrical components failure probabitities in order to reestablish the service. The results reflect an interesting potential of this approach and encourage further research on the topic.

Abstract
In this paper is presented a Game Theory based methodology to allocate transmission costs, considering cooperation and competition between producers. As original contribution, it finds the degree of participation on the additional costs according to the demand behavior. A comparative study was carried out between the obtained results using Nucleolus balance and Shapley Value, with other techniques such as Averages Allocation method and the Generalized Generation Distribution Factors method (GGDF). As example, a six nodes network was used for the simulations. The results demonstrate the ability to find adequate solutions on open access environment to the networks.

Abstract
This paper proposes a swarm intelligence long-term hedging tool to support electricity producers in competitive electricity markets. This tool investigates the long-term hedging opportunities available to electric power producers through the use of contracts with physical (spot and forward) and financial (options) settlement. To find the optimal portfolio the producer risk preference is stated by a utility function (U) expressing the trade-off between the expectation and the variance of the return. Variance estimation and the expected return are based on a forecasted scenario interval determined by a long-term price range forecast model, developed by the authors, whose explanation is outside the scope of this paper. The proposed tool makes use of Particle Swarm Optimization (PSO) and its performance has been evaluated by comparing it with a Genetic Algorithm (GA) based approach. To validate the risk management tool a case study, using real price historical data for mainland Spanish market, is presented to demonstrate the effectiveness of the proposed methodology.

Abstract
The development of automated individualized drug dosage regimens, namely in general anaesthesia environment, has been a subject of interest in the last decades. The use of continuous intravenous drug administration aims at, accurately, maintaining the system at a desired target effect concentration level. Different methods have been proposed for the design of individualized dosage regimens. In this study individual drug dose design is achieved through the characterization of transient initial response induced by a bolus administration of drug. This approach is based on the statistical analysis of the data using Walsh-Fourier spectral analysis which provides information about patient dynamics, allowing the on-line drug dose design using multiple linear least squares and quantile regression technics. The proposed methodology is illustrated in the case where the effect measured on the patient corresponds to the neuromuscular blockade (NMB) level and the drug to the muscle relaxant atracurium.

Abstract
This paper presents the participation of distributed generation and interruptible loads for Demand Side Management (DSM) in market environment. This contribution has two aspects, first, the technical requirements that should be implemented on these applications. Then the way DGs and ILs are offered in market and what should be included in their contracts. In this paper the above mentioned issues will be discussed and a database system will be presented by which a Disco can deal with interruptible loads and distributed generations simultaneously in its contracts.

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.