Energy and Buildings 82 (2014) 341–355 Contents lists available at ScienceDirect Energy and Buildings j ourna l ho me page: www.elsevier.com/locate/enbuild Occupant behavior and schedule modeling for building energy simulation through office appliance power consumption data mining Jie Zhao * , Bertrand Lasternas, Khee Poh Lam, Ray Yun, Vivian Loftness Center for Building Performance and Diagnostics, School of Architecture, Carnegie Mellon University, 5000 Forbes Avenue, MMCH-410-IW, Pittsburgh, PA 15213, USA a r t i c l e i n f o Article history: Received 28 April 2014 Received in revised form 3 July 2014 Accepted 15 July 2014 Available online 23 July 2014 Keywords: Occupant behavior Occupancy schedule Data mining Plug load Office appliance Energy simulation EnergyPlus Climate zone Decision tree Linear regression a b s t r a c t The occupants’ health, comfort, and productivity are important objectives for green building design and operation. However, occupant behavior also has “passive” impact on the building indoor environment by generating heat, CO 2 , and other “disturbances”. This study develops an “indirect” practical data min- ing approach using office appliance power consumption data to learn the occupant “passive” behavior. The method is tested in a medium office building. The average percentage of correctly classified indi- vidual behavior instances is 90.29%. The average correlation coefficient between the predicted group schedule and the ground truth is 0.94. The experimental result also shows a fairly consistent group occupancy schedule, while capturing the diversified individual behavior in using office appliances. Com- pared to the occupancy schedule used in the Department of Energy prototype medium office building models, the learned schedule has a 36.67–50.53% lower occupancy rate for different weekdays. The heating, ventilation, and air conditioning (HVAC) energy consumption impact of this discrepancy is inves- tigated by simulating the prototype EnergyPlus models across 17 different climate zones. The simulation result shows that the occupancy schedules’ impact on the building HVAC energy consumption has large variations for the buildings under different climate conditions. © 2014 Elsevier B.V. All rights reserved. 1. Introduction 1.1. “Active” role of occupants The occupants’ health, comfort, and productivity are considered as key objectives for green building design and operation. At the same time, the occupants play a critical “active” role in the build- ing operation. Occupant behavior and feedback are necessary to achieve the desired total building performance [1]. Numerous studies have developed various control systems and modeling methods to better assist occupants to play their “active” roles in buildings. Table 1 shows a summary of reviewed litera- tures of occupants’ “active” influence in buildings. 10 out of 15 studies demonstrate an energy impact of occupant behavior by using various individualized control systems and dashboards for building heating ventilation and air conditioning (HVAC), lighting and plug load systems. Four studies about post occupancy eval- uation and complain handling show the occupant feedback can be useful for building diagnostics. Another four studies show that * Corresponding author. Tel.: +1 412 268 1492. E-mail addresses: jayzhao@cmu.edu, jiezhao.cmu2010@gmail.com (J. Zhao). providing occupants with individualized controls can influence their thermal comfort. Three studies show that providing the occupants with individual controls can improve their subjective satisfaction towards their working environment. 1.2. “Passive” role of occupants The studies above suggest that the occupant’s “active” feedback and behavior has strong influence on the indoor environment and building HVAC, lighting, and plug load system energy consump- tions. Similarly, the occupant’s “passive” role also has impact on the building performance. Particularly, for the building thermal and indoor air quality performance, occupants are treated as “mobile heat and CO 2 sources”, which can influence the HVAC energy con- sumption to a great extent. Hence, the occupants are typically treated as “disturbances” in the HVAC control system. It is criti- cal to study the occupant individual behavior and group schedule to uncover this “passive” impact. The following studies show that the occupants “passive” behav- ior have a significant impact on building energy consumptions. The simulation study in Ref. [17] showed that “for a typical single- occupancy office room, compared to the standard or reference work style, the austerity work style consumes up to 50% less energy, http://dx.doi.org/10.1016/j.enbuild.2014.07.033 0378-7788/© 2014 Elsevier B.V. All rights reserved.