Forecasting the hydroelectric power generation of GCMs using machine learning techniques and deep learning (Almus Dam, Turkey)

Renewable energy is one of the most important factors for developed and sustainable societies. However, its utilization in electrical power grid systems can be very challenging regarding rates predictably. depends mainly on environmental conditions such as rainfall-runoff ratios temperature. Because that, expected production heavily fluctuates, which makes prediction calculation feed-in into challenging. The accurate forecasting a crucial issue management process. This paper presents results deploying Machine Learning Techniques short-term amount produced General Circulation Models (GCMs) Data by Almus Dam Hydroelectric Power Plant Tokat, Turkey. study demonstrates use modeling techniques hydropower process using predicted monthly hydroelectric generation data GCMs from 2018 to 2080. Decision Tree, Deep Learning, Generalized Linear, Gradient Boosted Trees Random Forest models are utilized forecast production. show that correlation value gradient boosted trees model equals 0.717, means successful present data. used each GCM scenario 4.5 8.5. there small differences between models, predictions going similar directions all these models.