Özet:

Increasing interest in green energy has popularized the generation of electrical energy, especially from solar energy. Due to the discrete nature of solar energy, future energy production forecasting is very important in terms of uninterrupted and environmentally friendly supply of electrical energy Therefore, it is clear that estimating solar radiation will be vital in planning and managing all processes, from electricity generation, transmission, distribution and consumption. In this study, one-year, six months, four months and two months hourly solar radiation estimation was performed on the hourly basis of four years’ solar radiation data obtained four years of hourly data from the station named Afyon Region of the 5th Regional Directorate of Meteorology (MBM), using the Auto Regressive Integrated Moving Average (ARIMA), a time-series analysis method, ridge regression, and lasso regression estimation models, which are regression models. In addition, the estimation results were improved by applying the Extraterrestrial Radiation Filter (DDIF) in the structures of the methods. The closeness of the relationship between the estimated values obtained by the methods used and the actual radiation values has been tried to be revealed with graphics and statistical methods.

Anahtar Kelimeler: