Wind Speed Prediction Using Meteorological Measurements for Elazığ Province

Authors : Serdal Polat, Nuh Alpaslan, Ibrahim Rıza Hallaç

Pages : 110-120

Doi:10.53070/bbd.1381841

View : 55 | Download : 67

Publication Date : 2023-12-20

Article Type : Research Paper

Abstract :As a result of the increasing energy demand and growing environmental concerns, the global significance of renewable energy resources is steadily rising. Wind energy has been increasingly gaining importance in electricity generation in recent years. The accurate prediction of wind speed is crucial for the safe operation of wind turbines. In this study, wind speed prediction performance of different models was examined using data obtained from various regions in the Elazığ province. LSTM, random forest, and XGBoost models were employed in the study. The dataset was decomposed into seasonal and trend components using the STL method, and seasonal components were determined using Fourier transformation. The results indicate that different models perform better in different regions. According to the findings, XGBoost and random forest models exhibit the lowest RMSE and MSE values in Elazığ, Keban, and Sivrice regions, indicating better predictions for these models in these areas.
Keywords : Hibrit model, LSTM, Random Forest, XGBoost, STL, FFT ve rüzgar hızı tahmini