A review of the role of AI integration with building energy management systems in enhancing building efficiency

Abstract

Amid the global emphasis on energy efficiency, efforts are being made in the Building Energy Management System (BEMS) field to mitigate climate change and reduce greenhouse gas emissions. A significant gap, referred to as the performance gap, exists between predicted and actual energy performance in buildings, posing challenges to energy efficiency. This study provides a comprehensive review of the factors contributing to the performance gap, such as the complexity of building systems, poor data quality and lack of data availability, poor maintenance, and the variability of occupant behaviour. Living in an era signified by extensive data and the fast-growing capabilities of Artificial intelligence (AI) presents opportunities to integrate AI into BEMS to enhance energy efficiency. The application of AI enables dynamic and adaptive control strategies as well as real-time adjustments based on building and environmental conditions. Through AI, systems can continuously learn from historical data and optimize energy consumption predictions, reducing the performance gap. This study highlights the pivotal role of various AI model applications in BEMS and their potential benefits in predicting a building's energy consumption and system performance for more sustainable buildings.