A Bayesian approach for probabilistic classification and inference of occupant thermal preferences in office buildings

Abstract

This paper presents a new data-driven method for learning personalized thermal preference profiles, by formulating a combined classification and inference problem, without developing different models for each occupant. Different from existing approaches, we developed a generalized thermal preference model in which our main hypothesis,-Different people prefer different thermal conditions‖, is explicitly encoded. The approach is fully Bayesian, and it is based on the premise that the thermal preference is mainly governed by (i) an overall thermal stress, represented using physical process equations with relatively few parameters along with prior knowledge of the parameters, and (ii) the personal thermal preference characteristic, which is modeled as a hidden random variable. The concept of clustering occupants based on this hidden variable, i.e., similar thermal preference characteristic, is introduced. The results, based on a dataset collected from a typical office building population, show clear evidence of the existence of multi-clusters; in particular, the 5-cluster model performed best compared to 2, 3 and higher cluster models using the studied dataset. Subsequently, the thermal preference of a new occupant in the dataset is inferred by using a mixture of the general sub-models for each cluster. The results show that the method developed in this study provides accurate predictions for personalized thermal preference profiles and it is efficient as it only requires a relatively small dataset collected from each occupant. The approach presented in this paper is a significant step towards personalized environments in office buildings using real-time feedback from occupants.

Using Thermostats for Indoor Climate Control in Office Buildings: The Effect on Thermal Comfort

“…This suggests that the ability to calculate comfort indices such as Fanger, or even the ability to build personalized comfort models for the building occupants [62][63][64][65][66] can enable a more comfort-aware and user-centric building design and operation. Here, building designers and energy modellers can estimate more accurately the future energy consumption of a building, by taking into account the energy required to ensure comfortable interiors (through proper control actions), instead of using fixed temperature set-points throughout yearly simulations.…”

Automated mobile sensing: Towards high-granularity agile indoor environmental quality monitoring

“…IEQ assessment can be conducted using occupant surveys [5,28,29,30], personal monitoring [31,32,33], and sensor measurements [34,35,36]. Surveys provide subjective IEQ evaluation from occupant perspectives; however, survey design requires systematic effort to avoid bias and confusion, and the results can not be updated frequently due to user fatigue.…”

“…In addition, while indoor environment is often inhomogeneous and unpredictable, the stationary sensors may not always be deployed in the optimal locations to reflect indoor environment. Personal monitoring systems, such as using infrared thermography [31] and physiological measurements [32,33,37] can offer assessment of individual comfort and inform building operation system of proper adjustments in real-time; however, they require users to be equipped with special instruments or sensors and may involve privacy concerns. For some IEQ parameters like indoor air quality, the effect on productivity and health may be long-term and cannot be readily captured by physiological measurements.…”

Approximate Dynamic Programming for Building Control Problems with Occupant Interactions

“…In particular, the thermal preferences of occupants induce their actions, which potentially perturb the thermal dynamics of building spaces. It is a special class of stochastic systems in the sense that the statistical behavior of the occupant's actions interact with the system evolution: occupant thermal preference models [6][7][8] depend on environmental factors, for example, the indoor air temperature. For this reason, developments of effective stochastic control methods become of prime importance.…”

“…Challenges: In building environment research, advanced occupant thermal preference models have been developed, e.g., [6][7][8], where occupant's thermal preferences are expressed as probability mass functions that depend on environmental factors, for example, the indoor air temperature. However, the existing results did not consider such occupant behavior models that interacts with the building dynamics.…”