PREDICTION OF SOLAR RADIATION BASED ON MACHINE LEARNING METHODS

Yıl 2017, Cilt: 2 Sayı: 1, 16 - 20, 15.06.2017

Rifat Hacioğlu

Öz

In this study, machine learning methods which linear regression and Gaussian process regression models are used to estimate the solar radiation on daily data set taken from the wind central in Zonguldak province in Turkey. The measured wind speed, temperature, pressure, humidity parameters together with solar radiation are used for the prediction process. In the prediction process, number of delay steps from 3 to 12 for these parameters are applied to the developed models. In order to determine the performance of the obtained model, the model is evaluated in terms of statistical error criteria such as MAE, MSE and RMSE. The least prediction error for the solar radiation prediction process is determined. It has been observed that Gaussian regression model approach provides a high performance to predict solar radiation with related to other measured parameters. 

Anahtar Kelimeler

Solar radiation, prediction, linear regression, Gaussian process regression, machine learning

Kaynakça

• C. Voyant, G. Notton, S. Kalogirou, M.L. Nivet, C. Paoli, F. Motte, and A. Fouilloy, “Machine learning methods for solar radiation forecasting: A review”, Renewable Energy, 105, 2017, pp. 569-582.
• S. Karasu, A. Altan, Z. Saraç, and R. Hacıoğlu, “Prediction of wind speed with non-linear autoregressive (NAR) neural networks”, IEEE 25th Signal Processing and Communications Applications Conference, 2017, pp. 1-4.
• S. Karasu, A. Altan, Z. Saraç, and R. Hacıoğlu, “Estimation of fast varied wind speed based on NARX neural network by using curve fitting”, International Conference on Advanced Technology & Sciences (ICAT’17), 2017, pp. 551-557.
• C. Voyant, C. Darras, M. Muselli, C. Paoli, M.L. Nivet, and P. Poggi, “Bayesian rules and stochastic models for high accuracy prediction of solar radiation”, Applied Energy, 114, 2014, pp. 218-226.
• K. Mohammadi, S. Shamshirband, M.H. Anisi, K.A. Alam, and D. Petkovic, “Support vector regression based prediction of global solar radiation on a horizontal surface”, Energy Conversion and Management, 91, 2015, pp .433-441.
• K. Mohammadi, S. Shamshirband, C.W. Tong, M. Arif, D. Petkovic, and S. Ch, “A new hybrid support vector machine–wavelet transform approach for estimation of horizontal global solar radiation”, Energy Conversion and Management, 92, 2015, pp. 162-171.
• A. Di Piazza, M.C. Di Piazza, and G. Vitale, “Solar and wind forecasting by NARX neural networks”, Renewable Energy and Environmental Sustainability, 39, 2016, pp. 1-5.
• L. Olatomiwa, S. Mekhilef, S. Shamshirband, and D. Petkovic, “Adaptive neuro-fuzzy approach for solar radiation prediction in Nigeria”, Renewable and Sustainable Energy Reviews, 51, 2015, pp. 1784-1791.
• C.E. Rasmussen and C.K.I. Williams, “Gaussian processes for machine learning”, MIT Press, 2006.
• A.G. Wilson, “Covariance kernels for fast automatic pattern discovery and extrapolation with Gaussian processes”, University of Cambridge, 2014.
• R.M. Neal, “Bayesian Learning for Neural Networks”, Toronto University Doctorate Thesis, 1995, p. 118.