Modeling hourly diffuse solar-radiation in the city of São Paulo using a neural-network technique

In this work, a perceptron neural-network technique is applied to estimate hourly values of the diffuse solar-radiation at the surface in Sao Paulo City, Brazil, using as input the global solar-radiation and other meteorological parameters measured from 1998 to 2001. The neural-network verification was performed using the hourly measurements of diffuse solar-radiation obtained during the year 2002. The neural network was developed based on both feature determination and pattern selection techniques. It was found that the inclusion of the atmospheric long-wave radiation as input improves the neural-network performance. On the other hand traditional meteorological parameters, like air temperature and atmospheric pressure, are not as important as long-wave radiation which acts as a surrogate for cloud-cover information on the regional scale. An objective evaluation has shown that the diffuse solar-radiation is better reproduced by neural network synthetic series than by a correlation model.

[1]  A. Rabl,et al.  The average distribution of solar radiation-correlations between diffuse and hemispherical and between daily and hourly insolation values , 1979 .

[2]  J. Soares,et al.  Modeling surface energy fluxes for Iperó, SP, Brazil: an approach using numerical inversion , 2002 .

[3]  Athanasios Sfetsos,et al.  Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques , 2000 .

[4]  F. J. Newland,et al.  A study of solar radiation models for the coastal region of South China , 1989 .

[5]  Marija Zlata Božnar,et al.  Improvement of Air Pollution Forecasting Models Using Feature Determination and Pattern Selection Strategies , 1998 .

[6]  A. Oliveira,et al.  A new shadow-ring device for measuring diffuse solar radiation at the surface , 2002 .

[7]  S. Anderson,et al.  A New Look at Calibration and Use of Eppley Precision Infrared Radiometers. Part II: Calibration and Use of the Woods Hole Oceanographic Institution Improved Meteorology Precision Infrared Radiometer* , 1999 .

[8]  C. T. Nguyen,et al.  Calculation of monthly average global solar radiation on horizontal surfaces using daily hours of bright sunshine , 1993 .

[9]  R. J. Stone.  Improved statistical procedure for the evaluation of solar radiation estimation models , 1993 .

[10]  L. Hadjioannou,et al.  On the diffuse fraction of daily and monthly global radiation for the island of Cyprus , 1996 .

[11]  M. Boznar,et al.  Perceptron neural network-based model predicts air pollution , 1997, Proceedings Intelligent Information Systems. IIS'97.

[12]  J. Duffie,et al.  Estimation of the diffuse radiation fraction for hourly, daily and monthly-average global radiation , 1982 .

[13]  C.C.Y. Ma,et al.  Statistical comparison of solar radiation correlations Monthly average global and diffuse radiation on horizontal surfaces , 1983 .

[14]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[15]  M. Iqbal.  An introduction to solar radiation , 1983 .

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

[17]  Josep Calbó,et al.  INFLUENCE OF THE GLOBAL RADIATION VARIABILITY ON THE HOURLY DIFFUSE FRACTION CORRELATIONS , 1999 .

[18]  P. Mlakar.  Determination of features for air pollution forecasting models , 1997, Proceedings Intelligent Information Systems. IIS'97.

[19]  Inge Dirmhirn,et al.  Strengths and limitations of the Liu and Jordan model to determine diffuse from global irradiance , 1983 .

[20]  A. Soler,et al.  Dependence on latitude of the relation between the diffuse fraction of solar radiation and the ratio of global-to-extraterrestrial radiation for monthly average daily values , 1990 .

[21]  V. V. Satyamurty,et al.  Estimation of symmetric and asymmetric hourly global and diffuse radiation from daily values , 1992 .

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

[23]  Amauri Pereira de Oliveira,et al.  Correlation models of diffuse solar-radiation applied to the city of São Paulo, Brazil , 2002 .

[24]  E. F. Bradley,et al.  A New Look at Calibration and Use of Eppley Precision Infrared Radiometers. Part I: Theory and Application , 1998 .

[25]  A. J. Machado,et al.  Diurnal evolution of solar radiation at the surface in the city of São Paulo: seasonal variation and modeling , 2002 .

[26]  Robert J. Schalkoff,et al.  Pattern recognition - statistical, structural and neural approaches , 1991 .

[27]  M. W Gardner,et al.  Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences , 1998 .

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

[29]  I. Reda,et al.  Pyrgeometer calibration at the National Renewable Energy Laboratory (NREL) , 2002 .

[30]  Benjamin Y. H. Liu,et al.  The interrelationship and characteristic distribution of direct, diffuse and total solar radiation , 1960 .