This paper details the design and implementation of a real-time energy monitoring system dedicated to tracking and analyzing heat and electrical energy consumption. The system integrates smart meters, leveraging communication protocols such as RS232, RS485, and Ethernet, and utilizes a PostgreSQL database for robust data management. Grafana is used for intuitive data visualization. To enhance energy planning, machine learning techniques, specifically the XGBoost algorithm, were applied to historical consumption data, achieving a Root Mean Square Error (RMSE) of 4.86 in demand prediction. The system’s design, including the integration of converters and smart meters, ensures seamless compatibility with existing infrastructure, aligning with the principles of Industry 4.0 and 5.0. The proposed solution offers valuable insights for improving energy efficiency, reducing operational costs, and facilitating sustainable energy management practices.