Search for: All records

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. 

Building performance discrepancies between building design and operation are one of the causes that lead many new designs fail to achieve their goals and objectives. A main factor contributing to the discrepancy is occupant behaviors. Occupants responding to a new design are influenced by several factors. Existing building performance models (BPMs) ignore or partially address those factors (called contextual factors) while developing BPMs. To potentially reduce the discrepancies and improve the prediction accuracy of BPMs, this paper proposes a computational framework for learning mixture models by using Generative Adversarial Networks (GANs) that appropriately combining existing BPMs with knowledge on occupant behaviors to contextual factors in new designs. Immersive virtual environments (IVEs) experiments are used to acquire data on such behaviors. Performance targets are used to guide appropriate combination of existing BPMs with knowledge on occupant behaviors. The resulting model obtained is called an augmented BPM. Two different experiments related to occupants lighting behaviors are shown as case study. The results reveal that augmented BPMs significantly outperformed existing BPMs with respect to achieving specified performance targets. The case study confirmed the potential of the computational framework for improving prediction accuracy of BPMs during design.