Crowd-Sourcing Thermostatic Control for Optimizing a Thermal Condition in an Open Workplace Environm
The design and operation of HVAC systems face a conflict goals between providing acceptable thermal comfort conditions and reducing HVAC performance relevant energy consumption. Integrating occupants’ thermal comfort preferences into the HVAC control algorithms has high potential to contribute to overcoming this conflict issue. Therefore, the goal of this study was to develop an optimal control algorithm to maximize energy conservation efficiency while enhancing the occupants’ thermal comfort and satisfactions.
Considering individual occupants’ different thermal preferences, two occupancy conditions were selected in this study: single-occupancy condition (SOC) and multi-occupancy condition (MOC). The control logic is different between SOC and MOC, but the control for SOC can be adopted as the fundamental principle of the multi-occupancy condition. The SOC experiments were conducted to survey subjects’ thermal sensation and comfort levels while the thermal environmental conditions changed from 65 ºF to 80 ºF in the climate chamber. Occupants’ thermal comfort data were collected through the SOC experiments and then each subject’s thermal preference profile was established based on the use of data-driven approaches. Meanwhile, subjects’ physical parameters were collected by skin sensors, heart rate sensors, and thermal scanners to confirm the correlation between the indoor thermal condition ad subjects’ physiological responses. An indoor temperature set-point has been configured by machine learning algorithm considering energy saving and thermal comfort in a multi-occupancy condition by using the advanced artificial intelligent algorithm to minimize the total thermal discomfort of the occupants. The study result confirmed the energy saving potential while sharing a single thermal setting between multiple occupants in a workplace environment.