基于循环特征与深度学习算法的建筑能耗预测方法研究

Research on Building Energy Consumption Prediction Method Based on Cycle Feature and Deep Learning Algorithm

为了提升智能建筑的能耗预测精度,提出了一种基于循环特征和深度学习算法的建筑能耗预测方法,并在计算过程中充分考虑了建筑能耗的周期循环特性,提升了预测的准确程度。利用频谱分析的手法提取了建筑的循环特征和残余能耗,利用深度学习的方法构建其预测模型。为了验证本文算法的有效性,将本文算法应用于商业建筑中,并与其他算法进行数据对比。结果证明,无论是与数据回归模型进行对比还是与其他学习方法进行对比,本文算法在预测精度和稳定程度上均有明显的优势,可用于预测建筑的能耗问题。

In order to improve the prediction accuracy of energy consumption of intelligent buildings,a prediction method of building energy consumption based on cycle characteristics and deep learning algorithm is proposed.The cycle characteristics of building energy consumption are fully considered in the calculation process,which improves the accuracy of prediction.The cycle characteristics and residual energy consumption of buildings are extracted by spectrum analysis,and the prediction model is constructed by deep learning method.In order to verify the effectiveness of this algorithm,this algorithm is applied to commercial buildings,and compared with other algorithms.The results show that,whether compared with the data regression model or with other learning methods,this algorithm has obvious advantages in prediction accuracy and stability,and can be used to predict the energy consumption of buildings.