Univariate and multivariate forecasting of hourly solar radiation with artificial intelligence techniques

Abstract This paper introduces a new approach for the forecasting of mean hourly global solar radiation received by a horizontal surface. In addition to the traditional linear methods, several artificial-intelligence-based techniques are studied. These include linear, feed-forward, recurrent Elman and Radial Basis neural networks alongside the adaptive neuro-fuzzy inference scheme. The problem is examined initially for the univariate case, and is extended to include additional meteorological parameters in the process of estimating the optimum model. The results indicate that the developed artificial intelligence models predict the solar radiation time series more effectively compared to the conventional procedures based on the clearness index. The forecasting ability of some models can be further enhanced with the use of additional meteorological parameters.

[1]  M. Collares-Pereira,et al.  TAG: A time-dependent, autoregressive, Gaussian model for generating synthetic hourly radiation , 1992 .

[2]  Chin-Teng Lin,et al.  Neural fuzzy systems , 1994 .

[3]  J. Olseth,et al.  The probability density and autocorrelation of short-term global and beam irradiance , 1992 .

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

[5]  L. Mora-López,et al.  Multiplicative ARMA models to generate hourly series of global irradiation , 1998 .

[6]  Vincenzo Cena,et al.  Stochastic simulation of hourly global radiation sequences , 1979 .

[7]  Michio Sugeno,et al.  Fuzzy identification of systems and its applications to modeling and control , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[9]  J.-S.R. Jang,et al.  Predicting chaotic time series with fuzzy if-then rules , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[10]  A. Germond,et al.  Short term electrical load forecasting with artificial neural networks , 1996 .

[11]  D.R. Hush,et al.  Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[12]  Saifur Rahman,et al.  Forecasting sub-hourly solar irradiance for prediction of photovoltaic output , 1987 .

[13]  J. Utans,et al.  Input variable selection for neural networks: application to predicting the U.S. business cycle , 1995, Proceedings of 1995 Conference on Computational Intelligence for Financial Engineering (CIFEr).

[14]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[15]  Zoran Obradovic,et al.  Rapid design of neural networks for time series prediction , 1996 .

[16]  William Remus,et al.  Can neural networks applied to time series forecasting learn seasonal patterns: an empirical investigation , 1994, 1994 Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences.

[17]  Les E. Atlas,et al.  Recurrent neural networks and robust time series prediction , 1994, IEEE Trans. Neural Networks.

[18]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[19]  L. Personnaz,et al.  The selection of neural models of nonlinear dynamical systems by statistical tests , 1994, Proceedings of IEEE Workshop on Neural Networks for Signal Processing.

[20]  Manuel Collares-Pereira,et al.  Statistical properties of hourly global radiation , 1992 .

[21]  Shuichi Hokoi,et al.  Stochastic models of solar radiation and outdoor temperature , 1990 .