Combined Cycle Power Plants offer an efficient and environmentally friendly means of electricity generation, albeit with challenges in accurately predicting power output. This study proposes a hybrid model to forecast the total electrical power load in these plants by leveraging key input variables. Five machine learning algorithms, including Categorical Boosting, Histogram-based Gradient Boosting Regression, Extreme Gradient Boosting Regression, Light Gradient Boosting Machine, and Support Vector Regression, were employed, with their predictions optimized using the Hunger Games Search algorithm. This integration resulted in five hybrid models, with the combination of Hunger Games Search and Categorical Boosting emerging as the most effective, demonstrating superior performance in test datasets with an R2 value of 0.9735 and a mean absolute error of 2.05525. The Hunger Games Search algorithm enhanced prediction accuracy by fine-tuning core algorithm parameters. Comprehensive case analysis and metric evaluation underscored the efficacy of the proposed model for hourly power load forecasting in Combined Cycle Power Plants, although the hybrid model combining Hunger Games Search and Support Vector Regression exhibited comparatively poorer performance in test datasets with R2 of 0.9551 and a mean absolute error of 2.71211. The recommendation to integrate Categorical Boosting with the Hunger Games Search algorithm stands as a robust strategy for enhancing power load prediction in these power plants, promising greater operational efficiency and reliability in electricity generation.