Prediction of combined cycle power plant electrical output power using machine learning regression algorithms

In order to monitor the performance and related efficiency of a combined cycle power plant (CCPP), in addition best utilization its output, it is vital predict full load electrical output. this paper, output CCPP was predicted employing practically efficient machine learning algorithms, including linear regression, ridge lasso elastic net random forest gradient boost regression. The original data came from an actual confidential plant, which working on for 6 years, with four major features: ambient temperature, relative humidity, atmospheric pressure, exhaust vacuum, one target (electrical per hour). Different regression measures were used, R2 (coefficient determination), MAE (Mean Absolute Error), MSE Squared RMSE (Root Mean MAPE Percentage Error). Research results revealed that model outperformed other models without using dimensionality reduction technique (PCA) highest 0.912 0.872, respectively, had lowest 0.872 % 1.039 %, respectively. Moreover, prediction dropped slightly after almost all algorithms used. novelty work summarized predicting based few features simpler than reported deep neural networks combined. That means lower cost less complicated procedure as each, however, resulting accepted according evaluation metrics