Estimation of solar radiation using modern methods

It is stated in the present study that extreme learning machines (ELM) will display a greater performance in solar radiation estimation compared to artificial neural networks (ANN). The data acquired from Karaman province during 2010-2018 were used for evaluating the performance of the suggested approach. It was put forth when results were compared that ELM has displayed a greater estimation performance. Moreover, ANN and ELM were tested with different activation functions in order to obtain the best estimation response. While the best estimation result for ANN was obtained with the tansig function as 0.9828, mean square error (MSE) was obtained as 0.000129. The best estimation result for ELM was obtained with the sin function as 0.991 and MSE was calculated as 0.000881. Additionally ELM, training time 0.295 s, test time 0.266 s, MSE time 0.558 s was obtained. ELM displayed a high estimation performance in a very short amount of time. The ELM achieved a root mean square error (RMSE) value of 0.0297. This algorithm has achieved high accuracy with minimal error. Confidence interval estimations were carried out for the acquired correlation coefficients and the results were compared. ELM estimation performance is better than ANN with 95% confidence interval. (C) 2020 THE AUTHORS. Published by Elsevier BV on behalf of Faculty of Engineering, Alexandria University.

Automated summary

The study indicates that Extreme Learning Machines (ELM) outperform Artificial Neural Networks (ANN) in solar radiation estimation. Different activation functions were tested, with ELM showing better estimation performance. ELM achieved high accuracy with minimal error in a short amount of time, surpassing ANN.