Abstract
This paper presents a new approach to incipient fault diagnosis in power transformers, based on the results of dissolved gas analysis. A set of autoassociative neural networks or autoencoders are trained, so that each becomes tuned with a particular fault mode. Then, a parallel model is built where the autoencoders compete with one another when a new input vector is entered and the closest recognition is taken as the diagnosis sought. A remarkable accuracy is achieved with this architecture, in a large data set used for result validation. © 2011 IEEE.

Abstract
This paper analyzes the application of clustering techniques for wind power scenario reduction. The results have shown the unimodal structure of the scenario generated under a Monte Carlo process. The unimodal structure has been confirmed by the modes found by the information theoretic learning mean shift algorithm. The paper also presents a new technique able to represent the wind power forecasting uncertainty by a set of representative scenarios capable of characterizing the probability density function of the wind power forecast. From an initial large set of sampled scenarios, a reduced discrete set of representative scenarios associated with a probability of occurrence can be created finding the areas of high probability density. This will allow the reduction of the computational burden in stochastic models that require scenario representation. © 2011 IEEE.

Abstract
The inevitable wind power forecast errors result in differences between forecasted and observed wind power. To mitigate their economic impact, combining the wind power with pumped hydro energy storage may be used. In order to deliver a joint operational strategy for a wind power plant combined with storage, one requires reliable wind power forecasts. The forecasts commonly only consist of a single-value forecast (point forecast) for each look-ahead time. However, additional representative information concerning the forecast uncertainty may be required. In this paper, the influence of uncertainty representation daily operation for a wind power plant combined with pumped hydro storage is discussed. The paper illustrates how uncertainty representations such as Gaussian uncorrelated errors may also not be satisfactory. Based on a case study with a wind power plant combined with pumped hydro storage, organized for illustrative purposes, the paper demonstrates the need to have uncertainty representation including cross-period dependencies, in order to define a correct operation policy. © 2011 IEEE.

Abstract
In order to deal with the power fluctuations that come from wind uncertainties, this paper presents a generating reliability assessment of the real generation system of Bosnia and Herzegovina (BH) including wind power as an planning exercise for a given horizon. For this purposes, the sequential Monte Carlo simulation is used not only to assess conventional reliability indices as loss of load probability, loss of load expectation, loss of load frequency, and loss of load duration, but also to discuss an alternative measure of risk-based level called Well-being Analysis. © 2011 IEEE.

Abstract
This paper describes a new technique aimed at representing wind power forecasting uncertainty by a set of discrete scenarios able to characterize the probability density function of the wind power forecast. From an initial large set of sampled scenarios, a reduced discrete set of representative or focal scenarios associated with a probability of occurrence is created using clustering techniques. The advantage is that this allows reducing the computational burden in stochastic models that require scenario representation. The validity of the reduction methodology has been tested in a simplified Unit Commitment (UC) problem.

Abstract
Metaheuristics Algorithms are widely recognized as one of most practical approaches for Combinatorial Optimization Problems. This paper presents a comparison between two metaheuristics to solve a problem of Phase Balancing in Low Voltage Electric Distribution Systems. Among the most representative mono-objective metaheuristics, was selected Simulated Annealing, to compare with a different metaheuristic approach: Evolutionary Particle Swarm Optimization. In this work, both of them are extended to fuzzy domain to modeling a multi-objective optimization, by mean of a fuzzy fitness function. A simulation on a real system is presented, and advantages of Swarm approach are evidenced.