Abstract
The increasing volatility introduced to power grids by renewable energy sources makes it necessary that the accuracy of energy forecasts are improved. Photovoltaic (PV) power plants hold the biggest share of installed capacity of renewable energy in Germany, so that high quality PV power forecasts are vital for a cost efficient operation of the underlying electrical grid. In this paper, we evaluate multiple Numerical Weather Prediction (NWP) parameters for their ability to improve PV power forecasting features. The importance of features is decided by a Random Forest algorithm. Furthermore, the resulting top ranked features are tested by performing PV power forecasts with Support Vector Regression, Random Forest, and linear regression models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
meteocontrol GmbH: www.meteocontrol.com.
- 2.
European Centre for Medium-Range Weather Forecasts: www.ecmwf.int.
References
Bailey, T., Jain, A.K.: A note on distance-weighted k-nearest neighbor rules. IEEE Trans. Syst. Man Cybern. 8, 311–313 (1978)
Brabec, M., Pelikán, E., Krc, P., Eben, K., Musilek, P.: Statistical modeling of energy production by photovoltaic farms. In: 2010 IEEE Electric Power and Energy Conference (EPEC), pp. 1–6, August 2010
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Chang, C.-C., Lin, C.-J.: LIBSVM – a library for support vector machines (2015). Website, last checked 11 Feb 2016
Chen, C., Duan, S., Cai, T., Liu, B.: Online 24-h solar power forecasting based on weather type classification using artificial neural network. Sol. Energy 85(11), 2856–2870 (2011)
Fontoynont, M., Dumortier, D., Heinnemann, D., Hammer, A., Olseth, J., Skarveit, A., Ineichen, P., Reise, C., Page, J., Roche, L., et al.: Satellight: a WWW server which provides high quality daylight and solar radiation data for Western and Central Europe. In: 9th Conference on Satellite Meteorology and Oceanography, pp. 434–437. American Meteorological Society, Boston (1998)
Gala, Y., Fernández, Á., Díaz, J., Dorronsoro, J.R.: Support vector forecasting of solar radiation values. In: Pan, J.-S., Polycarpou, M.M., Woźniak, M., Carvalho, A.C.P.L.F., Quintián, H., Corchado, E. (eds.) HAIS 2013. LNCS (LNAI), vol. 8073, pp. 51–60. Springer, Heidelberg (2013). doi:10.1007/978-3-642-40846-5_6
Genuer, R., Poggi, J.-M., Tuleau-Malot, C.: Variable selection using random forests. Pattern Recogn. Lett. 31(14), 2225–2236 (2010)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Hastie, T., Tibshirani, R., Friedman, J.: The Elements of Statistical Learning. Springer, Berlin (2001)
Jurado, S., Peralta, J., Nebot, A., Mugica, F., Cortez, P.: Short-term electric load forecasting using computational intelligence methods. In: 2013 IEEE International Conference on Fuzzy Systems (FUZZ), pp. 1–8, July 2013
Kramer, O., Gieseke, F.: Short-term wind energy forecasting using support vector regression. In: Corchado, E., Snásel, V., Sedano, J., Hassanien, A.E., Calvo, J.L., Ślȩzak, D. (eds.) SOCO 2011. Advances in Intelligent and Soft Computing, vol. 87, pp. 271–280. Springer, Heidelberg (2011)
Krömer, P., Musílek, P., Pelikán, E., Krc, P., Jurus, P., Eben, K.: Support vector regression of multiple predictive models of downward short-wave radiation. In: 2014 International Joint Conference on Neural Networks, IJCNN 2014, Beijing, China, 6–11 July 2014, pp. 651–657 (2014)
Lorenz, E., Hurka, J., Heinemann, D., Beyer, H.G.: Irradiance forecasting for the power prediction of grid-connected photovoltaic systems. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 2(1), 2–10 (2009)
Louppe, G., Wehenkel, L., Sutera, A., Geurts, P.: Understanding variable importances in forests of randomized trees. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 26, pp. 431–439. Curran Associates Inc., Red Hook (2013)
Mandal, P., Madhira, S.T.S., Haque, A.U., Meng, J., Pineda, R.L.: Forecasting power output of solar photovoltaic system using wavelet transform and artificial intelligence techniques. Procedia Comput. Sci. 12, 332–337 (2012)
Marquez, R., Coimbra, C.F.: Forecasting of global and direct solar irradiance using stochastic learning methods, ground experiments and the NWS database. Sol. Energy 85(5), 746–756 (2011)
Mellit, A.: Artificial intelligence technique for modelling and forecasting of solar radiation data: a review. Int. J. Artif. Intell. Soft Comput. 1, 52 (2008)
Monteiro, C., Santos, T., Fernandez-Jimenez, L., Ramirez-Rosado, I., Terreros-Olarte, M.: Short-term power forecasting model for photovoltaic plants based on historical similarity. Energies 6(5), 2624–2643 (2013)
Oshiro, T.M., Perez, P.S., Baranauskas, J.A.: How many trees in a random forest? In: Perner, P. (ed.) MLDM 2012. LNCS (LNAI), vol. 7376, pp. 154–168. Springer, Heidelberg (2012). doi:10.1007/978-3-642-31537-4_13
Pedro, H.T., Coimbra, C.F.: Assessment of forecasting techniques for solar power production with no exogenous inputs. Sol. Energy 86(7), 2017–2028 (2012)
Pelland, S., Remund, J., Kleissl, J., Oozeki, T., De Brabandere, K.: Photovoltaic and solar forecasting: state of the art (2013). http://www.iea-pvps.org/index.php?id=1&eID=dam_frontend_push&docID=1690
scikit learn. Machine learning in Python (2016). Website, last checked 11 Feb 2016
Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14, 199–222 (2004)
Wirth, H., Schneider, K.: Recent facts about photovoltaics in Germany, April 2016. http://www.ise.fraunhofer.de/en/renewable-energy-data/data-and-facts-about-pv
Wolff, B., Kühnert, J., Lorenz, E., Kramer, O., Heinemann, D.: Comparing support vector regression for PV power forecasting to a physical modeling approach using measurement, numerical weather prediction, and cloud motion data. Sol. Energy 135, 197–208 (2016)
Zeng, J., Qiao, W.: Short-term solar power prediction using a support vector machine. Renew. Energy 52, 118–127 (2013)
Acknowledgements
We like to thank meteocontrol GmbH for providing the PV system measurements as well as the ECMWF for numerical weather prediction forecasts that are basis of our experimental analysis. Björn Wolff is funded by the PhD program “System Integration of Renewable Energies” (SEE) of the University of Oldenburg promoted by the Lower Saxony Ministry for Science and Culture (MWK).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Wolff, B., Kramer, O., Heinemann, D. (2017). Selection of Numerical Weather Forecast Features for PV Power Predictions with Random Forests. In: Woon, W., Aung, Z., Kramer, O., Madnick, S. (eds) Data Analytics for Renewable Energy Integration. DARE 2016. Lecture Notes in Computer Science(), vol 10097. Springer, Cham. https://doi.org/10.1007/978-3-319-50947-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-50947-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50946-4
Online ISBN: 978-3-319-50947-1
eBook Packages: Computer ScienceComputer Science (R0)