Architecture Engineers Award

Optimizing building performance requires acknowledging the stochastic nature of occupant control behaviors, which significantly influence energy consumption, thermal comfort, and visual comfort outcomes. Traditional building performance models often rely on oversimplified behavioral assumptions and demand extensive computational time for stochastic simulations. This study proposes a novel optimization framework specifically designed to address uncertainty in occupant behavior while improving computational efficiency and solution robustness in building design optimization. Methodological Integration of Stochastic and Intelligent Optimization Techniques The proposed approach integrates Sample Average Approximation (SAA) with Monte Carlo simulations to obtain convergent mean performance estimates under uncertainty. To accelerate optimization, machine learning (ML) models are coupled with a Pareto-based Genetic Algorithm (GA), enabling rapid prediction of building performance metrics acr...

Traditional building energy simulation models often overlook the stochastic behavior of occupants and the complex interactions between multiple devices. This limitation creates a significant gap between predicted and actual building energy consumption. Addressing this issue requires behavior-sensitive frameworks that integrate both human and technical dimensions of building performance. The proposed study bridges this gap by introducing a fuzzy multi-criteria decision-making (FMCDM) approach coupled with evolutionary optimization to ensure realistic and adaptive performance predictions. Significance of Occupant Behavior in Energy Modeling Occupant behavior is one of the most influential yet uncertain factors in determining building energy performance. Stochastic patterns, such as irregular use of appliances, varying thermal preferences, and diverse daily routines, make deterministic models insufficient. Incorporating behavioral diversity through FMCDM provides more accurate results, ...