A multi-objective optimization framework for building performance under climate change

Most building energy simulations utilize typical meteorological year data, overlooking the impacts of climate change. This can lead to inaccurate predictions and suboptimal designs. This study develops an optimization framework to identify robust building designs under varying climate scenarios. A case study is presented for residential buildings in Huangshan, China under 2020, 2050 and 2020-2050 conditions. A general circulation model provides future weather data. Multi-objective optimization maximizes energy efficiency and minimizes life cycle costs. Machine learning models predict heating, cooling and cost as functions of envelope parameters. Optimization is performed using a genetic algorithm. Results reveal the optimum insulation thickness, wall properties and window specifications. Compared to 2020 data, the ideal roof insulation increases from 40 mm to 90 mm by 2050. The optimal heating transmittance decreases from 0.38 W/m2K to 0.19 W/m2K. The approach highlights the significant influence of evolving climate on building design. It provides architects with accurate projections to make informed design decisions for energy efficiency and cost savings over the building lifespan.