 This paper proposes a machine learning algorithm for short-term wind power forecasting. The proposed algorithm was tested using 16 parameters from the wind energy system and compared against four other algorithms, like GBM, Random Forest, CatBoost, and XGBoost. The results showed that the Random Forest algorithm performed best during training, while the CatBoost algorithm demonstrated superior performance with an RMS-E of 13.84 for the test set, as determined by 10-fold cross-validation. This article was authored by G. Pankumer, S. J. Aprakash, and Karthik Kenegarathanam.