Abstract

Abstract
This paper describes the methodology developed to build estimates of electricity prices having the horizon of one week. This approach uses artificial neural networks and includes a particular treatment of weekends and national holidays as a way to improve the quality of the results. The developed approach was tested using data obtained from the Spanish market operator for the time period of 2006 to 2008. The obtained value of MAPE - Mean Absolute Percentage Error - was 12,62% for workdays and 10,73% for holidays and weekends. The obtained results show that this study has interest to the market agents in question, since realistic forecasting was achieved.

Abstract
This letter proposes a new concept applied to state estimation based on replacing traditional regression models by a criterion of maximizing error correntropy introducing a novel way to identify and correct large errors.

Abstract
This paper reports new results in adopting entropy concepts to the training of neural networks to perform wind power prediction as a function of wind characteristics (speed and direction) in wind parks connected to a power grid. Renyi's entropy is combined with a Parzen windows estimation of the error pdf to form the basis of two criteria (minimum entropy and maximum correntropy) under which neural networks are trained. The results are favorably compared in online and offline training with the traditional minimum square error (MSE) criterion. Real case examples for two distinct wind parks are presented.

Abstract
Incipient fault diagnosis is closely related to insulation condition assessment. A great number of methods are available for condition monitoring and diagnosis of power transformer insulation systems, but only few of them can take direct measurements inside the transformer. Fiber optic sensors can be applied to incipient fault diagnosis. In particular, acoustic sensors have been developed for detection and location of partial discharges in oil-filled power transformers. We report the study of extrinsic and intrinsic fiber Fabry-Perot sensors that can be used to detect the acoustic waves that are generated by a partial discharge inside a power transformer. A comparative analysis is done to determine the best sensing head configuration and some methods to improve the parameter readout sensitivity are proposed. The sensing head behaviour when immersed in different fluids (air, water, and oil) is also investigated. (c) 2009 Society of Photo-Optical Instrumentation Engineers. [DOI: 10.1117/1.3080752]

Abstract
This paper presents an application of evolutionary particle swarm optimization (EPSO)-based methods to evaluate power system reliability. Population-based (PB) methods appear as competitors to the traditional Monte Carlo simulation (MCS), because they are computationally efficient in estimating a variety of reliability indices. The work reported in this paper demonstrates that EPSO variants can focus the search in the region of the state space where contributions to the formation of a reliability index may be found, instead of conducting a blind sampling of the space. The results obtained with EPSO are compared to MCS and with other PB methods.