DIGITAL TWINS IN BUILDING ENERGY MANAGEMENT FOR ELECTRICITY CONSUMPTION FORECASTING AND ENERGY EFFICIENCY IMPROVEMENT

• Datum: 2026
• 1. Verfasser: Shpak, Denys
• Format: Artikel
• Sprache: Englisch
• Veröffentlicht: General Energy Institute of the National Academy of Sciences of Ukraine 2026
• Schlagworte: digital twin; building; electricity consumption forecasting; energy efficiency; IoT; BMS/EMS; machine learning; optimization.
• Online Zugang: https://systemre.org/index.php/journal/article/view/962
• Назва журналу: System Research in Energy

The article examines the application of digital twins as a tool for modernizing building energy management aimed at electricity consumption forecasting and improving energy efficiency. Based on a review of contemporary approaches, the study analyzes how the integration of BIM/semantic models, IoT data, and operational systems with machine learning methods enables the implementation of a closed-loop control framework. Methods for electricity consumption forecasting are systematized according to time horizons and their suitability for operational tasks. Typical scenarios for improving energy efficiency through the use of digital twins are presented. A methodological framework for the implementation of digital twins in buildings is proposed, taking into account measurement and verification, model drift, interoperability, and cybersecurity. The impact of digital twins on the quality of managerial decision-making is identified, particularly in enhancing energy consumption controllability and enabling a transition to proactive control of building engineering systems based on predictive models and scenario analysis, as well as in creating conditions for the development of more flexible and sustainable building energy systems. The practical implementation cycle of digital twins in building energy management is generalized. Key limitations of digital twin deployment in buildings are outlined. The dependence of digital twin effectiveness on data consistency and the correctness of energy management problem formulation is demonstrated.