LAUSR

Abstract Many technical solutions have been developed to reduce buildings’ energy consumption, but limited efforts have been made to adequately address the role or action of building occupants in this process. Our earlier investigations have shown that occupants play a significant role in buildings’ energy consumption: It was shown that savings of up to 20% could be achieved by modifying occupant behavior thorough direct feedback and recommendations. Studying the role of occupants in building energy consumption requires an understanding of the interrelationships between climatic conditions; building characteristics; and building services and operation. This paper describes the development of a systematic procedure to provide building occupants with direct feedback and recommendations to help them take appropriate action to reduce building energy consumption. The procedure is geared toward developing a Reference Building (RB) (an energy-efficient building) for a specific given building. The RB is then compared against its given building to inform the occupants of the given building how they are using end-use loads and how they can improve them. The RB is generated using a data-mining approach, which involves clustering analysis and neural networks. The framework is based on clustering similar buildings by effects unrelated to occupant behavior. The buildings are then grouped based on their energy consumption, and those with lower consumption are combined to generate the RB. Performance evaluation is determined by comparison of a given building with an RB. This comparison provides feedback that can lead occupants to take appropriate measures (e.g., turning off unnecessary lights or heating, ventilation, and air conditioning (HVAC), etc.) to improve building energy performance. More accurate, scalable, and realistic results are achiveable through current methodology which is shown through comparison with existing literature.