Design of Robust Green Buildings Using a Non-probabilistic Uncertainty Analysis Method

Uncertainty analysis has become an active research area in the field of building energy analysis because most of parameters are inherently uncertain in buildings. Most of previous studies implement probabilistic-based uncertainty analysis, which requires detailed information to define probability for input factors. However, it is hard to obtain detailed information for these inputs, especially at the initial design stage of a building project. Therefore, this paper applies the non-probabilistic Dempster-Shafer theory of evidence approach for uncertainty analysis in an office building using the EnergyPlus program. The results indicate that the Dempster-Shafer theory can be very useful to provide pertinent and reliable results by taking into account the level of available information in the design stage of building projects for sustainable buildings. The reliable machine learning models can be constructed in order to reduce high computational cost of this non-probabilistic uncertainty analysis method.