建筑用户行为节能潜力评估新方法
2018-05-23胡宾俞准李郡张国强
胡宾 俞准 李郡 张国强



摘要:现有建筑用户行为节能潜力评估方法未能充分考虑不同用户之间的差异性,从而显著降低了评估结果的准确性。针对此种不足,提出一种行为节能潜力评估的新方法。首先通过主成分分析对用户行为影响因素进行降维处理,在此基础上采用数据挖掘方法中的聚类分析技术对样本用户进行合理分类,并针对不同类用户特征分别进行节能潜力评估。由于该方法既全面考虑了同一用户不同因素的影响,又充分体现了不同用户之间的差异性,可显著提高评估结果的准确性。通过将其应用于湖南省3所高校100名研究生用户电脑待机行为的节能潜力评估表明,该方法是有效和可行的。
关键词:用户行为;节能潜力评估;数据挖据;聚类分析;主成分分析
中图分类号:TU244.3 文献标志码:A文章编号:16744764(2018)02010306
收稿日期:20170610
基金项目:国家自然科学基金资助(51408205);中央高校基本科研业务费专项资金资助()
作者简介:胡宾(1991),女,主要从事建筑节能及行为节能研究,Email:binh8284@foxmail.com。
俞准(通信作者),男,副教授,博士生导师,Email:zhunyu@hnu.edu.cn。
Received:20170610
Foundation item:National Natural Science Foundation of China (No.51408205); The Fundamental Research Funds for the Central Universities
Author brief:Hu Bin (1991), graduate student, main research interest: Building energy saving and standby energy,Email:binh8284@foxmail.com.
Yu Zhun (corresponding author), Associate professor,Email:zhunyu@hnu.edu.cn.A new energysaving potential evaluation method for building
occupant behavior improvement
Hu Bin,Yu Zhun,Li Jun,Zhang Guoqiang
(College of Civil Engineering,Hunan University, Changsha 410082, P.R.China)
Abstract:Existing energysaving potential evaluation methods for building occupant behavior improvement do not take occupants diversity into consideration. This significantly decreases the accuracy of evaluation results. To address this issue, a new energysaving potential evaluation method has been established. First, principal component analysis is used to reduce the number of influencing factors of occupant behavior. Then, a data mining technique, clustering analysis is used to classify sample occupants into different groups. At last, energysaving potentials are evaluated in terms of different groups characteristics. This method takes both the impact of various influencing factors and the diversity of occupants into account, and thus can improve the evaluation accuracy significantly. The method was applied to evaluate the energysaving potential of 100 graduate students computer standby usage behavior in 3 universities in Hunan province. The results demonstrate its effectiveness and feasibility.
Keywords:Occupant behavior; Energysaving potential evaluation; Data mining; Clustering analysis; Principal component analysis
研究表明建筑用戶行为对建筑总能耗有显著的影响,且通过改变用户行为减少能耗是实现建筑节能的有效手段之一[12]。为深入分析用户行为对建筑能耗的影响和有效降低建筑能耗,有必要对行为节能的潜力进行量化分析和评估。当前对行为节能潜力的研究涵盖不同行为类型[34](如正常使用行为和待机行为)、不同建筑类型[57](如住宅建……
