Application of Surrogate Models for Building Envelope Design Exploration and Optimization

Building performance simulations are usually timeconsuming. They may account for the major portion of time spent in Computational Design Optimization (CDO), for instance, annual hourly daylight and energy simulations. In this case, the optimization may become less efficient or even infeasible within a limited time frame of real-world projects, due to the computationally expensive simulations. To handle the problem, this research aims to investigate the potentials of surrogate models (i.e. Response Surface Methodology - RSM) to be used in the building envelope design exploration and optimization that consider visual and energy performance. Specifically, the work investigates how, and to what extent, 1) problem scales may affect the application of RSM, and 2) different ways of using RSM may affect the quality of Pareto Front approximations. Thus, a series of multi-objective optimization tests are carried out; preliminary discussion is made based on the current results.