Combining context-aware design-specific data and building performance models to improve building performance predictions during design

Chokwitthaya, Chanachok; Zhu, Yimin; Dibiano, Robert; Mukhopadhyay, Supratik

doi:10.1016/j.autcon.2019.102917

Building performance models (BPMs) are often used to estimate, analyze, and understand the performance of future or non-existing buildings during designs. However, performance gaps between prediction from BPMs and actual building still exist. Obviously, occupant behaviors are one of the major factors which cause the performance gaps because of several reasons, including (1) they are dynamic, (2) they are driven by many contextual factors, and (3) they are difficult to be captured by traditional experiments. This paper discusses a framework of applying generative adversarial networks (GANs) as an alternative approach to combine existing BPMs with occupant responses to design specific and context sensitive factors obtained from immersive virtual environment (IVE) toward designed buildings (target buildings) in order to reduce performance gaps between prediction during designs and actual buildings.

More Like this