Comparison of Wavelet Artificial Neural Network, Wavelet Support Vector Machine, and Adaptive Neuro-Fuzzy Inference System Methods in Estimating Total Solar Radiation in Iraq

Estimating the amount of solar radiation is very important in evaluating energy that can be received from sun for construction power plants. Using machine learning tools to estimate a helpful method. With high number sunny days, Iraq has potential using energy. This study used Wavelet Artificial Neural Network (WANN), Support Vector Machine (WSVM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) techniques at Wasit Dhi Qar stations Iraq. RMSE, EMA, R2, IA criteria were evaluate performance compare results with actual measured value. The showed WANN WSVM methods had similar modeling. However, technique slightly better than technique. In stations, value R2 was 0.89 0.86, respectively. 0.88 0.87, ANFIS also obtained acceptable results. compared other two techniques, lower, 0.84 0.83