B. García-Domingo

Characterization of Concentrating Photovoltaic modules by cooperative competitive Radial Basis Function Networks

Concentrating Photovoltaic (CPV) technology attempts to optimize the efficiency of solar energy production systems. As conventional Photovoltaic (PV) technology, suffers from variability in its production and needs models for determining the exact module performance. There are several problems when analyzing CPV systems performance with traditional techniques due to absence of standardization. In this sense it is remarkable the importance for the emerging CPV technology, of the existence of models which allow the prediction of modules performance from initial atmospheric conditions. In this paper, a CPV module is studied by means of atmospheric conditions obtained using an automatic test and measuring system developed by the authors. The characterization of the CPV module is carried out considering incident normal irradiance, ambient temperature, spectral irradiance distribution and wind speed. CO^2RBFN, a cooperative-competitive algorithm for the design of radial basis neural networks, is adapted and applied to these data obtaining a model with a good level of accuracy on test data, improving the results obtained by other methods considered in the experimental comparison. These results are promising and the obtained model could be used to work out the maximum power at the CPV reporting conditions and to analyze the performance of the module under any conditions and at any moment.

MEFES: An evolutionary proposal for the detection of exceptions in subgroup discovery. An application to Concentrating Photovoltaic Technology

Subgroup discovery is a broadly applicable data mining technique whose main objective is the search for descriptions of subgroups of data that are statistically unusual with respect to a property of interest. The obtaining of general rules describing as many instances as possible is preferred in subgroup discovery, but this can lead to less accurate descriptions that incorrectly describe some instances. Under certain conditions, these incorrectly-described instances can be grouped into exceptions. A new post-processing methodology for the detection of exceptions associated to previously discovered subgroups is presented in this paper. The purpose is to obtain a new description to improve the accuracy of the initial subgroup and to describe new small spaces in data with unusual behaviour within the subgroup. This post-processing methodology can be applied to the results of any subgroup discovery algorithm. A post-processing multiobjective evolutionary fuzzy system is developed following this methodology, the Multiobjective Evolutionary Fuzzy system for the detection of Exceptions in Subgroups (MEFES). A wide experimental study has been performed, supported by statistical tests, comparing the results obtained by representative subgroup discovery algorithms with those obtained after applying the post-processing algorithm. Finally, MEFES is applied in a real problem related to the description of the behaviour of a type of solar cell in the Concentrating Photovoltaic area providing useful information to the experts.

A differential evolution proposal for estimating the maximum power delivered by CPV modules under real outdoor conditions

Multivariable model to calculate the maximum power given by concentrating modules.Spectrum additional indexes in the equation proposed by the standard methodology.Calculation of regression coefficients by a differential evolution algorithm.Applicability to the forecasting of the energy produced by big power plants. Concentrating photovoltaics is an innovative alternative to flat-plate module to produce cost-competitiveness electricity. It is based on the use of optical system of reduced cost which is able to concentrate the solar light on a very small surface (high efficiency solar cell). At present, this technology has a marginal position in photovoltaic market and to take off needs to increase the confidence of the public and private sector. A better understanding of the concentrating photovoltaics technology electrical performance under real meteorological conditions would improve this situation. Because the bankability of a concentrating photovoltaics plant is addressed through the modelling of its energy production, an accurate estimation of the maximum power of the these modules is crucial to achieve it. Accordingly, the commercial evolution of concentrating photovoltaic technology demands prediction models for estimating the maximum power delivered by a concentrating photovoltaic module under real atmospheric conditions. Until now the only established standard method for outdoor power rating of this type of modules (ASTME-2527-09, defined by the American Society for Testing and Materials) does not consider the impact of the direct normal irradiance spectral distribution. The solar spectrum has an important influence on the electric performance of multijunction solar cells which composes concentrating photovoltaic modules.In this work, an analysis of the inclusion in the prediction model of the solar spectrum by means of two indexes (spectral matching ratio and the average photon energy) and different spectral intervals is performed. Then, a differential evolution proposal for the estimation of regression coefficients for the two multivariable regression models is described. The accurate calculation of the model parameters reveals relations among the atmospheric conditions very useful for the experts. The multivariable regression models have been applied to two different concentrating photovoltaic modules, obtaining mean absolute percentage error values within the range 1.91-3.94%. The use of these accurate models for the estimation of the maximum power would allow to estimate the electric production of a concentrating photovoltaic power plant and the analysis of its costs and profitability, with the consequent benefits for the commercial development of this technology.

An evolutionary fuzzy system for the detection of exceptions in subgroup discovery

Subgroup Discovery (SD) is a data mining technique whose main objective is the search for descriptions of subgroups of data that are statistically unusual with respect to a property of interest. General rules describing as many instances as possible are preferred in SD, but this can lead to less accurate descriptions that incorrectly describe some instances. These negative examples can be grouped into exceptions. The paper presents a new evolutionary fuzzy system for the detection of exceptions associated to rules previously obtained by a SD algorithm. Considering the initial subgroup and associated exceptions, the aim is to obtain a new description in order to increase the accuracy of the initial subgroup. This algorithm can be applied to the results of any SD algorithm. An experimental study shows the utility of the proposal, which is also applied in a real problem related to concentrating photovoltaic technology, providing useful information to the experts.

A Performance Study of Concentrating Photovoltaic Modules Using Neural Networks: An Application with CO2RBFN

Concentrating Photovoltaic (CPV) technology attempts to optimize the efficiency of solar energy production systems and models for determining the exact module performance are needed. In this paper, a CPV module is studied by means of atmospheric conditions obtained using an automatic test and measuring system. CO2RBFN, a cooperative-competitive algorithm for the design of radial basis neural networks, is adapted and applied to these data obtaining a model with a good level of accuracy on test data, improving the results obtained by other methods considered in the experimental comparison. These initial results are promising and the obtained model could be used to work out the maximum power at the CPV reporting conditions and to analyze the performance of the module under any conditions and at any moment.