Smart and predictive heating system: Belief model for indoor regulation

The objective of this paper is to investigate a method to model data uncertainties in order to regulate a smart heating system that reduces energy consumption. To achieve this, we propose a multilevel data fusion system that provides a contextual trend, based on the belief theory of Dempster-Shafer for data combination and the Transferable Belief Model (TBM) to take the decision. The fusion system combines the weather forecast and the thermal comfort associated to the occupant's activities and habits. The challenge we took is complex as the data to be fused are highly uncertain and heterogeneous but our method proved its efficiency as we obtain very satisfactory simulation results.