Makine Öğrenmesi Algoritmalarını Kullanarak Rüzgar Enerjisi Üretimi Tahmini

Renewable energy becomes progressively popular in the world because renewable resources such as solar, geothermal, wind are clean, inexhaustible and come from natural sources. Wind is one of most significant it plays a key role generation electricity. Thus, accurate power estimation crucial to deal with challenges balance trading, planning, scheduling decisions strategies generation. This study proposes prediction model solve real-life problem sector by accurately estimating amount production per hour next 24 hours applying machine learning (ML) techniques using historical data weather forecasting reports. In proposed approach, first, an unsupervised ML method (i.e., K-Means clustering algorithm) applied group into meaningful clusters; then, these clusters accepted new feature values added dataset enlarge it; finally, supervised regression) performed for prediction. compares nine algorithms: K-Nearest Neighbors, Support Vector Regression, Random Forest, Extra Trees, Gradient Boosting, Ridge Least Absolute Shrinkage Selection Operator, Decision Tree, Convolutional Neural Network. The aim this investigate success different algorithms on real-world turbines propose methodology benchmark various choose final