摘要
利用经典时间序列大数据预测模型(ARIMA)作为优化改造后的多参数预测模型,对建筑逐时能源消耗进行预测,研究建筑使用需求参数对建筑能耗预测的影响规律。在大数据预测模型中引入建筑使用需求参数,如室外环境、室内环境、人员参数等,研究不同参数的引入对能耗预测模型预测结果精度的影响。引入影响能耗参数之后,建筑逐时能耗预测精度有不同程度提升。其中,人员参数对于建筑能耗预测精度提升最为显著。多项参数同时引入模型时可将预测精度进一步提升。能耗预测精度影响程度排序为:人员参数>室外环境参数>室内环境参数。
The classical time series big data prediction model(ARIMA)is used as the multi-parameter prediction model following the optimization and retrofitting,to predict the hourly energy consumption of the building,and to study the impact of building demand parameters on building energy consumption prediction.In the big data prediction model,the demand parameters about the outdoor environment,indoor environment,staff parameters,and the varieties,are introduced and studied on their influence on the predicting accuracy of the energy consumption prediction model.The accuracy of building hourly energy consumption prediction is improved to varying degrees after introducing parameters that affect energy consumption.Among them,the staff parameter is the most significant for the prediction accuracy of building energy consumption.When multiple parameters are introduced into the model at the same time,the prediction accuracy can befurther improved.The influence degree of energy consumption prediction accuracy is ranked as follows:staff parameter>outdoor environmental parameter>indoor environmental parameter.
作者
赵海湉
王需
林波荣
朱颖心
张菁华
孙弘历
ZHAO Hai-tian;WANG Xu;LIN Bo-rong;ZHU Ying-xin;ZHANG Jing-hua;SUN Hong-li(School of Architecture,Tsinghua University,Beijing 100084,China;Architectural Design and Research Institute of Tsinghua University,Beijing 100084,China)
出处
《建筑节能》
CAS
2020年第7期39-42,共4页
BUILDING ENERGY EFFICIENCY
基金
国家重点研发计划项目“基于全过程的大数据绿色建筑管理技术研究与示范”(2017YFC0704200)
