Abstract
In this paper, we propose an air-conditioning control methodology based on prediction of occupant's request.Our method enables to predict how an occupant wants to operate switches on the air-conditioner control panel in certain thermal environment using the Bayesian Networks. To show our basic concept and detailed procedure, we first provide the structure of Bayesian Networks for this application. Next, we show probability tables which presents the probabilistic distribution of occupant's requests at each temperature width. After that, using an example case, we describe how to predict occupant's requests and how to update probability tables. Finally, we confirm our proposed method discussing our experimental results.
