Selection of input parameters to model direct solar irradiance by using artificial neural networks

A very important factor in the assessment of solar energy resources is the availability of direct irradiance data of high quality. However, this component of solar radiation is seldom measured and thus must be estimated from data of global solar irradiance, which is registered in most radiometric stations. In recent years, artificial neural networks (ANN) have shown to be a powerful tool for mapping complex and non-linear relationships. In this work, the Bayesian framework for ANN, named as automatic relevance determination method (ARD), was employed to obtain the relative relevance of a large set of atmospheric and radiometric variables used for estimating hourly direct solar irradiance. In addition, we analysed the viability of this novel technique applied to select the optimum input parameters to the neural network. For that, a multi-layer feedforward perceptron is trained on these data. The results reflect the relative importance of the inputs selected. Clearness index and relative air mass were found to be the more relevant input variables to the neural network, as it was expected, proving the reliability of the ARD method. Moreover, we show that this novel methodology can be used in unfavourable conditions, in terms of limited amount of available data, performing successful results.

[1]  Hans Henrik Thodberg,et al.  A review of Bayesian neural networks with an application to near infrared spectroscopy , 1996, IEEE Trans. Neural Networks.

[2]  J. Garrison.  A study of the division of global irradiance into direct and diffuse irradiance at thirty-three U.S. sites , 1985 .

[3]  Jouko Lampinen,et al.  Bayesian approach for neural networks--review and case studies , 2001, Neural Networks.

[4]  E. Maxwell.  A quasi-physical model for converting hourly global horizontal to direct normal insolation , 1987 .

[5]  Francisco J. Batlles,et al.  Estimation of hourly global photosynthetically active radiation using artificial neural network models , 2001 .

[6]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[7]  Radford M. Neal,et al.  Bayesian Learning for Neural Networks (Lecture Notes in Statistical Vol. 118) , 1997 .

[8]  C. Long,et al.  SURFRAD—A National Surface Radiation Budget Network for Atmospheric Research , 2000 .

[9]  Mohamed Mohandes,et al.  Estimation of global solar radiation using artificial neural networks , 1998 .

[10]  W. Beckman,et al.  Diffuse fraction correlations , 1990 .

[11]  Francisco J. Batlles,et al.  Estimation of hourly direct normal from measured global solar irradiance in Spain , 2000 .

[12]  Yoshishige Kemmoku,et al.  DAILY INSOLATION FORECASTING USING A MULTI-STAGE NEURAL NETWORK , 1999 .

[13]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[14]  Christopher K. I. Williams,et al.  Using Bayesian neural networks to classify segmented images , 1997 .

[15]  William D. Penny,et al.  Bayesian neural networks for classification: how useful is the evidence framework? , 1999, Neural Networks.

[16]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[17]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[18]  G. Hoogenboom,et al.  Development of a neural network model to predict daily solar radiation , 1994 .

[19]  A. Rapti.  Atmospheric transparency, atmospheric turbidity and climatic parameters , 2000 .