Research on Prediction and Regulation of Thermal Dissatisfaction Rate Based on Personalized Differences

Thermal discomfort body language has been shown to be a psychological representation of personnel’s particular thermal comfort. Individual comfort differences are ignored in public building settings with random personnel flow. To solve this issue, we suggested Bayesian group dissatisfaction rate prediction model based on expression and subsequently implemented intelligent indoor temperature humidity control. The PMV-PPD was utilized represent the group’s overall create prior distribution rate. acquire dynamic language, data were collected real-world office setting experiment. Based theory, used personalized expressions modify universal realized assessment by combining commonality personalization. Finally, deep reinforcement learning system employed achieve results show that when combined, real-time high accuracy good performance, provides reference basis for reasonable settings.