Deducing the classification rules for thermal comfort controls using optimal method

This study investigates the feasibility of using a rule set of human thermal sensation index to control a heating ventilation and air conditioning (HVAC) system in order to achieve a desired thermal comfort level and energy savings. A novel approach based on an optimization method is developed to deduce the rules of learning human thermal comfort. In contrast to conventional thermal comfort levels, the proposed approach explains the linguistic rules in an "If . . . Then" form, in which proposed thermal comfort levels do not require an iterative solution and can be easily adjusted, depending on the specific thermal sensation of occupants. Results of this study demonstrate that the proposed thermal comfort control mechanism can also be implemented to achieve thermal comfort, energy savings, and reduce computational costs.