Abstract
We study an automatic procedure for selecting the most useful external variables for solar power forecasting. We use Genetic Algorithm (GA) as combinatorial optimisation tool of these feature variables. As forecasting model we use a particular case of Neural Network named Echo State Networks (ESN), which has been successfully used in the community for solving temporal learning problems. We study more than 20 weather variables that can impact on the solar power, and we compare the obtained results by GAs with the Spearman’s rank correlation coefficient. Our approach is evaluated on a well-known public dataset, and we obtain promising results.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cox, B., Cohen, A.: Human Universe. William Collins (2014)
Pedro, H.T.C., Coimbra, C.F.M.: Assessment of forecasting techniques for solar power production with no exogenous inputs. Solar Energy 86(7), 2017–2028 (2012)
Basterrech, S., Prokop, L., Burianek, T., Misak, S.: Optimal design of neural tree for solar power prediction. In: Proccedings of the 2014 15th International Scientific Conference on Electric Power Engineering (EPE), pp. 273–278, May 2014
Basterrech, S., Zjavka, L., Prokop, L., Misak, S.: Irradiance prediction using echo state queueing networks and differential polynomial neural networks. In: 2013 13th International Conference on Intelligent Systems Design and Applications (ISDA), pp. 271–276, Dec 2013
Chen, C., Duan, S., Cai, T., Liu, B.: Online 24-h solar power forecasting based on weather type classification using artificial neural network. Solar Energy 85, 2856–2870 (2011)
Bacher, P., Madsen, H., Nielsen, H.A.: Online short-term solar power forecasting. Solar Energy 83, 1772–1783 (2009)
Letendre, S., Makhyoun, M., Taylor, M.: Predicting solar power production: irradiance forecasting models, applications and future prospects. Technical report, Solar Electric Power Association, Washington, DC, USA, March 2014. www.solarelectricpower.org
Pelland, S., Remund, J., Kleissl, J., Oozeki, T., De Brabandere, K.: Photovoltaic and solar forecasting: state of art. Technical Report IEA PVPS T14 01:2013, International Energy Agency Photovoltaic Power Systems Programme (2013). http://www.iea-pvps.org
Andreas, A., Wilcox, S.: Aurora, colorado (data). Technical Report DA-5500-56491, Solar Technology Acceleration Center (SolarTAC), Colorado, USA (2011). doi:10.5439/1052224
Robinzonov, N., Tutz, G., Hothorn, T.: Boosting techniques for nonlinear time series models. AStA Adv. Stat. Anal. 96(1), 99–122 (2012)
Holland, J.H.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975)
Reeves, C.R.: Genetic alogarithms for the opertions researcher. INFORMS J. Comput. 9(3), 231–250 (1997)
Blum, C., Roli, A.: Metaheuristics in combinatorial optimization: overview and conceptual comparison. ACM Comput. Surv. 35(3), 268–308 (2003)
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks. Technical Report 148, German National Research Center for Information Technology (2001)
Verstraeten, D., Schrauwen, B., D’Haene, M., Stroobandt, D.: An experimental unification of reservoir computing methods. Neural Netw. 20(3), 287–289 (2007)
Reservoir computing approaches to recurrent neural network training: Lukos̆evic̆ius, M., Jaeger, H. Comput. Sci. Rev. 3, 127–149 (2009)
Butcher, J.B., Verstraeten, D., Schrauwen, B., Day, C.R., Haycock, P.W.: Reservoir computing and extreme learning machines for non-linear time-series data analysis. Neural Netw. 38, 76–89 (2013)
Acknowledgments
This work was supported by Grant of SGS No. SP2016/97, VŠB-Technical University of Ostrava, Czech Republic.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Basterrech, S., Snášel, V. (2016). Feature Selection Using a Genetic Algorithm for Solar Power Prediction. In: Abraham, A., Kovalev, S., Tarassov, V., Snášel, V. (eds) Proceedings of the First International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’16). Advances in Intelligent Systems and Computing, vol 450. Springer, Cham. https://doi.org/10.1007/978-3-319-33609-1_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-33609-1_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-33608-4
Online ISBN: 978-3-319-33609-1
eBook Packages: EngineeringEngineering (R0)