Heating, ventilation and air-conditioning (HVAC) accounts for around 40% of the total building energy consumption. It has therefore become a major target for reductions, in terms of both energy usage and CO2 emissions. In the light of progress in building intelligence and energy technologies, traditional methods for HVAC optimization, control, and fault diagnosis will struggle to meet essential requirements such as energy efficiency, occupancy comfort and reliable fault detection. Machine learning and data science have great potential in this regard, particularly with developments in information technology and sensor equipment, providing access to large volumes of high-quality data. There remains, however, a number of challenges before machine learning can gain widespread adoption in industry. This review summarizes the recent literature on machine learning for HVAC system optimization, control and fault detection. Unlike other reviews, we provide a comprehensive coverage of the applications, including the factors considered. A brief overview of machine learning and its applications to HVAC is provided, after which we critically appraise the recent literature on control, optimization and fault diagnosis and detection. Finally, we provide a comprehensive discussion on the limitations of current research and suggest future research directions.
Zhou et al. (Fri,) studied this question.