Integrating Random Forest and Support Vector Regression Models for Optimized Energy Consumption Evaluation in Cloud Computing Data Centers

This study proposes a novel approach for energy consumption evaluation in cloud computing data centers. The immense energy consumption of these data centers presents significant environmental and economic challenges. Traditional evaluation methods often fail to provide accurate estimations due to the complex dynamics of cloud computing environments. The research introduces an integrated model, combining Random Forest Regression and Support Vector Regression, along with a Gradient Boosting Regressor for iterative training of regression parameters. We measure the model's performance using Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE), replacing traditional relative deviation measures. The proposed approach aims to provide more accurate and efficient energy consumption evaluations, offering potential benefits in energy management, operational costs reduction, and minimizing environmental impact.