The potential of novel data mining models for global solar radiation prediction
- 30 Downloads
Advance knowledge of solar radiation is highly essential for multiple energy devotions such as sustainability in energy production and development of solar energy system. The current research investigates the capability of four data mining computation models, namely random forest (RF), random tree, reduced error pruning trees and hybrid model of random committee with random tree reduce (RC) for predicting daily measured solar radiation at four locations of Burkina Faso, i.e., Bur Dedougou, Bobo-Dioulasso, Fada-Ngourma and Ouahigouya. Daily data of seven climatic variables, namely maximum and minimum air temperature, maximum and minimum relative humidity, wind speed, evaporation and vapor pressure deficit, for the period 1998–2012 are used for solar radiation prediction. Different combinations of input variables are used according to correlation coefficient between the predictors and predictand, and the best input combination is selected based on the sensitivity of model output measured in terms of statistical indices. The obtained results are found consistence for all the meteorological stations. The highest accuracy in prediction is found when all the climate variables are used as input. The RC and RF showed the minimal absolute error in prediction at all the stations. The RMSE and NSE are found in the range of 0.03–0.05 and 0.77–0.91 for RC and 0.03–0.05 and 0.78–0.92 for RF at different stations. The results indicate that the proposed data mining models can be used for accurate prediction of solar radiation over the Burkina Faso.
KeywordsData mining models Solar radiation prediction Climate variables Burkina Faso region
The authors would like to reveal their gratitude and appreciation to the provider of the climatological data: The National Agency of Meteorology—Burkina Faso.
Compliance with ethical standards
Conflict of interest
There is no conflict to declare on publishing this paper.
- Aybar-Ruiz A, Jiménez-Fernández S, Cornejo-Bueno L et al (2016) A novel grouping genetic algorithm–extreme learning machine approach for global solar radiation prediction from numerical weather models inputs. Sol Energy 132:129–142. https://doi.org/10.1016/j.solener.2016.03.015 CrossRefGoogle Scholar
- Jagielski R (2000) Genetic programming prediction of solar activity. In: Intelligent data engineering and automated learning—IDEAL 2000: data mining, financial engineering, and intelligent agentsGoogle Scholar
- Kumar M, Raghuwanshi N, Singh R et al (2002) Estimating evapotranspiration using artificial neural network. J Irrig Drain Eng 128:224–233. https://doi.org/10.1061/(ASCE)0733-9437(2002)128:4(224) CrossRefGoogle Scholar
- Mohamed WNHW, Salleh MNM, Omar AH (2013) A comparative study of reduced error pruning method in decision tree algorithms. In: Proceedings—2012 IEEE international conference on control system, computing and engineering, ICCSCE 2012Google Scholar
- REN21 (2015) Renewables 2015-global status reportGoogle Scholar
- REN21 (2017) Renewables 2017: global status reportGoogle Scholar
- Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San FranciscoGoogle Scholar
- Witten IH, Frank E (2011) Data mining: practical machine learning tools and techniques. Morgan Kaufmann, BurlingtonGoogle Scholar
- Youssef AM, Pourghasemi HR, Pourtaghi ZS, Al-Katheeri MM (2016) Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia. Landslides. https://doi.org/10.1007/s10346-015-0614-1 Google Scholar
- Zhang P, Takano H, Murata J (2011) Daily solar radiation prediction based on wavelet analysisGoogle Scholar