Building energy consumption prediction based on parameter sensitivity analysis and genetic algorithm

Building is one of the main areas of energy consumption, and its demand for energy accounts for a significant proportion. The "verification based" energy-saving design of buildings is one of the main reasons for the high energy consumption of buildings. To address this issue, this study proposes an energy consumption prediction model applied to building conceptual design. This model uses the Morris algorithm to conduct sensitivity analysis on the main factors affecting building energy consumption, and ranks them according to the magnitude of their impact. Based on sensitivity analysis, the crossover and mutation factors of genetic algorithm were improved according to the ranking of influencing factors. The case analysis shows that the model prediction results of building energy consumption are basically consistent with the analysis results of energy analysis software. The energy consumption error for building cooling is 5.86%, and the energy consumption error for heating is 4.02%, meeting the energy consumption prediction requirements during the conceptual design phase. The proposed model advances building energy-saving design to the conceptual design stage, which helps to integrate energy consumption prediction throughout the entire process of building design, greatly improving the quality and efficiency of building design.