以某大型房地产公司所建建筑为研究对象,通过相关性分析,确定影响公用建筑电力能耗的关键因素。基于关键影响因素,采用BP神经网络算法,建立建筑能耗密度预测模型,对比观测值和预测值之间的残差,结果表明预测模型具有较好的准确性。 Taking the construction of a large real estate company as the research object, through the correlation analysis, the key factors affecting the power consumption of public buildings are determined. Based on the key influencing factors, BP neural network algorithm was used to establish the building energy density prediction model, and the residual between the observed and predicted values ​​was compared. The results show that the prediction model has good accuracy.