Solar Radiation Modeling with Adaptive Approach

Abstract

The unsustainable formation of fossil fuels, increase the interest on different resources and  this leads to greater emphasis on clean resources. Solar energy is one of the popular sources among the renewables. Electricity generation from PV panels directly related to the solar radiation value measured on surface of the panel. Modeling of solar radiation is important due to manage the integration of different sources to the grid. In this study, previously developed Adaptive Approach method is used for modeling the solar radiation values. This method combines linear prediction filter method with an empiric approach. Linear prediction filter used in this study utilize the current value of the solar radiation to predict next hour’s solar radiation value while the empiric model utilize from the current value of the solar radiation and the deviation on extraterrestrial radiation. One year solar radiation data belong to Van region is used in this study. The accuracies of the forecasting results are compared and discussed.

Keywords

• Solar radiation forecasting,Adaptive approach,Empiric model,Linear prediction filter

References

1. [1]. K. Benmouiza and A. Cheknane, “Forecasting hourly global solar radiation using hybrid k-means and nonlinear autoregressive neural network models,” Energy Convers. Manag., vol. 75, pp. 561–569, Nov. 2013.
2. [2]. J. R. Trapero, N. Kourentzes, and A. Martin, “Short-term solar irradiation forecasting based on Dynamic Harmonic Regression,” Energy, vol. 84, pp. 289–295, May 2015.
3. [3]. Y. Kashyap, A. Bansal, and A. K. Sao, “Solar radiation forecasting with multiple parameters neural networks,” Renew. Sustain. Energy Rev., vol. 49, pp. 825–835, Sep. 2015.
4. [4]. Y. Gala, Á. Fernández, J. Díaz, and J. R. Dorronsoro, “Hybrid machine learning forecasting of solar radiation values,” Neurocomputing, vol. 176, pp. 48–59, May 2015.
5. [5]. M. Ghayekhloo, M. Ghofrani, M. B. Menhaj, and R. Azimi, “A novel clustering approach for short-term solar radiation forecasting,” Sol. Energy, vol. 122, pp. 1371–1383, Dec. 2015.
6. [6]. L. Mazorra Aguiar, B. Pereira, M. David, F. Díaz, and P. Lauret, “Use of satellite data to improve solar radiation forecasting with Bayesian Artificial Neural Networks,” Sol. Energy, vol. 122, pp. 1309–1324, Dec. 2015.
7. [7]. F. O. Hocaoğlu, Ö. N. Gerek, and M. Kurban, “Hourly solar radiation forecasting using optimal coefficient 2-D linear filters and feed-forward neural networks,” Sol. Energy, vol. 82, no. 8, pp. 714–726, Aug. 2008.
8. [8]. E. Akarslan, F. O. Hocaoğlu, and R. Edizkan, “A novel M-D (multi-dimensional) linear prediction filter approach for hourly solar radiation forecasting,” Energy, vol. 73, pp. 978–986, Aug. 2014.

9. [9]. E. Akarslan and F. O. Hocaoglu, “A novel adaptive approach for hourly solar radiation forecasting,” Renew. Energy, vol. 87, pp. 628–633, Mar. 2016.
10. [10]. R. G. Allen, “Environmental, and E. Water Resources Institute,” Task Comm. Stand. Ref. ASCE Stand. Ref. evapotranspiration equation. Reston, Va. Am. Soc. Civ. Eng., 2005.
11. [11]. N. Z. Al-Rawahi, Y. H. Zurigat, and N. A. Al-Azri, “Prediction of hourly solar radiation on horizontal and inclined surfaces for Muscat/Oman,” J. Eng. Res., vol. 8, no. 2, pp. 19–31, 2011.
12. [12]. P. T. Nastos, A. G. Paliatsos, K. V. Koukouletsos, I. K. Larissi, and K. P. Moustris, “Artificial neural networks modeling for forecasting the maximum daily total precipitation at Athens, Greece,” Atmos. Res., vol. 144, pp. 141–150, Jul. 2014.
13. [13]. K. P. Moustris, I. C. Ziomas, and A. G. Paliatsos, “3-Day-Ahead Forecasting of Regional Pollution Index for the Pollutants NO2, CO, SO2, and O3 Using Artificial Neural Networks in Athens, Greece,” Water, Air, Soil Pollut., vol. 209, no. 1–4, pp. 29–43, Aug. 2009.