基于BP神经网络的公用建筑电力能耗预测研究

Research on Power Consumption Prediction of Public Buildings Based on BP Neural Network

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 buildings that constructed by a large real estate company as the research object,the paper determines the key factors affecting the power consumption of public buildings through the correlation analysis. Based on the factors,uses the BP neural network algorithm to establish the prediction model of building energy consumption density,compares the residual between the observed value and the predicted value,the results show that the predition model has good accuracy.