A SURROGATE-ASSISTED OPTIMIZATION APPROACH TO IMPROVE THERMAL COMFORT AND ENERGY EFFICIENCY OF SPORTS HALLS IN SUBTROPICAL CLIMATES

Balancing the thermal comfort and energy efficiency has been recognized as a critical issue in sports hall design, which is yet to be properly implemented in early design stages due to the huge computational cost and delayed simulation feedback. This paper develops an accelerated optimization approach for thermal comfort and energy efficiency of sports halls by combining surrogate modelling with evolutionary algorithms. An integrated computational workflow designated for early-stage application was established that consists of Design of experiments, Surrogate modelling, Surrogateassisted multi-objective optimization, and Multi-criteria decision making. Specifically, a parametric sports hall model was set up for batch physics-based simulations to generate abundant training samples, which was then utilized to develop surrogate models for the rapid prediction of thermal comfort and energy efficiency. The validated surrogate models were eventually linked with evolutionary algorithms to quickly identify the optimal design solution(s). The performance of the developed approach was evaluated against the traditional simulation-based optimization (SBMOO) method. Results indicated that the proposed approach could save 70.91% of total computational time for this case study, whilst achieving better optimized thermal comfort and energy efficiency with a reduction of mean PMV and site EUI by 0.001 and 1.60 kWh/m2/yr versus the SBMOO method.