The increasing global energy demand necessitates building energy efficiency design as a key driver of sustainability. Traditional methods often prioritise single objectives, failing to meet comprehensive performance requirements. This study proposes a multi-objective evolutionary algorithm combined with an improved particle swarm optimisation algorithm for building energy efficiency design. A multi-surrogate model assists in reducing simulation costs and enhancing optimisation accuracy. Results demonstrate that the method achieves a better balance between energy consumption and comfort. Its energy consumption in single office buildings and multi-residential buildings was reduced by 29.58% and 0.67% respectively compared to the comparative method, and the duration of discomfort was reduced by 11.79% and 1.57% respectively. The optimised approach also decreases computation time substantially. This research provides an efficient and practical tool for sustainable building design, supporting energy conservation and carbon reduction in the construction sector.
Tang et al. (Thu,) studied this question.