This paper proposes a machine learning-based algorithm and enhanced green network model for energy-efficient computing in data centers. The model aims to reduce the energy consumption of data centers while maintaining optimal performance. The proposed model collects data about the usage patterns and power consumption of the data center and preprocesses it for feature engineering. Feature engineering is performed to select the most relevant features for the model. A machine learning model is trained using the preprocessed data to predict power consumption and adjust system settings accordingly. The model is evaluated using a separate set of data to test its accuracy and reliability. Once the model is trained and evaluated, it is deployed in the data center for power management decisions. The performance of the model is continuously monitored to ensure that it is still accurate and reliable. The proposed model has the potential to significantly reduce energy consumption in data centers, which can have a positive impact on the environment and reduce operating costs. The results of the study demonstrate the feasibility and effectiveness of using machine learning for energy-efficient computing in data centers.