Application of group screening to dynamic building energy simulation models

Abstract

In order to select the most influential parameters of a building thermal model, a group screening technique was conducted. This technique uses regression analysis and experimental Plackett and Burman designs. After 136 simulations, 23 factors were selected from the initial set of 390. We came to the conclusion that global output variations (obtained with all parameters) can be accurately predicted from these 23 parameters. On the other hand, the results confirmed that group screening can be employed in the case of the building energy models despite the fact that the signs of the parameter effects are unknown. For the analysed configuration, the effects were found to be strongly influenced by the exchanged heat flows. In addition, the influential parameters (with respect to the inner air temperature) were all related to the building components having the largest heat exchange with the air cell.

Keywords:

• Deterministic building energy model
• group screening
• saturated designs
• plackett and burman designs
• regression analysis
• least squares