[1]杨昊,冉茂宇.基于BPT-MLR模型的建筑能耗分析和预测[J].华侨大学学报(自然科学版),2023,44(2):178-186.[doi:10.11830/ISSN.1000-5013.202211006]
　YANG Hao,RAN Maoyu.Analysis and Prediction of Building Energy Consumption Based on BPT-MLR Model[J].Journal of Huaqiao University(Natural Science),2023,44(2):178-186.[doi:10.11830/ISSN.1000-5013.202211006]
点击复制

基于BPT-MLR模型的建筑能耗分析和预测()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第44卷
期数:
2023年第2期
页码:
178-186
栏目:
出版日期:
2023-03-14

文章信息/Info

Title:
Analysis and Prediction of Building Energy Consumption Based on BPT-MLR Model
文章编号:
1000-5013(2023)02-0178-09
作者:
杨昊1; 2;  冉茂宇1; 2
1. 华侨大学 建筑学院, 福建 厦门 361021;2. 华侨大学 厦门市生态建筑营造重点实验室, 福建 厦门 361021
Author(s):
YANG Hao1; 2;  RAN Maoyu1; 2
1. School of Architecture, Huaqiao University, Xiamen 361021, China; 2. Xiamen Key Laboratory of Ecological Building Construction, Huaqiao University, Xiamen 361021, China
关键词:
建筑能耗;  平衡点温度;  多元线性回归;  BP神经网络;  预测分析
Keywords:
building energy consumption;  balance point temperature;  multiple linear regression;  BP neural network;  prediction analysis
分类号:
TU111.195
DOI:
10.11830/ISSN.1000-5013.202211006
文献标志码:
A
摘要:
通过对福建省厦门市某高校8栋公寓楼的房间日平均用电量的分析,提出一种建筑能耗的平衡点温度-多元线性回归(BPT-MLR)模型.使用统计方法识别平衡点温度,并根据该平衡点温度分段对房间日平均用电量进行多元线性回归预测分析;对8个参数进行筛选,最终选4个参数作为模型变量,包括1个数值型变量(室外空气平均温度)和3个定类型变量(性别、节假日指数和晴雨天指数).结果表明:对比3种数据驱动模型,BPT-MLR模型的预测性能最优,其R2值达到了95.29%,比BP神经网络模型和多元线性回归模型的R2值分别高出0.04%和24.64%.
Abstract:
A balance point temperature-multiple linear regression(BPT-MLR)model for building energy consumption analysis and prediction is proposed by analyzing the average daily electricity consumption of rooms in 8 apartment buildings in a university in Xiamen City, Fujian Province. A statistical method is used to identify BPT, and a MLR prediction analysis is performed for the average daily room electricity consumption based on this BPT segment. 8 parameters are screened and 4 parameters are finally selected as model variables, including 1 numerical type variable(average outdoor air temperature)and 3 fixed type variables(gender, holiday index and sunny day index). The results show that the BPT-MLR model has the best prediction performance when comparing 3 data-driven models, with R2 value 95.29%, which is 0.04% and 24.64% higher than that of the BP neural network model and MLR model respectively.

参考文献/References:

[1] ASHRAE.ASHRAE handbook: Fundamentals[M].Atlanta:American Society of Heating,Refrigerating,and Air-Conditioning Engineers,2013.
[2] YU Zhun,CHEN Jiayu,SUN Yongjun,et al.A GA-based system sizing method for net-zero energy buildings considering multi-criteria performance requirements under parameter uncertainties[J].Energy Buildings,2016,129:524-534.DOI:10.1016/j.enbuild.2016.08.032.
[3] LIU Ren,WANG Zhonghang,CHEN Haihong,et al.Overview of the application of energy consumption forecast models in energy efficiency optimization[J].IOP Conference Series:Earth and Environmental Science,2021,831:012012.DOI:10.1088/1755-1315/831/1/012012.
[4] AMBER K P,ASLAM M W,MAHMOOD A,et al.Energy consumption forecasting for university sector buildings[J].Energies,2017,10(10):1579.DOI:10.3390/en10101579.
[5] ZHANG Lei,SANG Guochen,CUI Xiaoling,et al.Design optimization of rural building in dry-hot and dry-cold area using a back propagation(BP)neural network[J].Energy Buildings,2022,259:111899.DOI:10.1016/j.enbuild.2022.111899.
[6] AISYAH S,SIMAREMARE A A,ADYTIA D,et al.Exploratory weather data analysis for electricity load forecasting using SVM and GRNN: Case study in Bali, Indonesia[J].Energies,2022,15(10):3566.DOI:10.3390/en15103566.
[7] SRETENOVI A,?IVKOVI B,JOVANOVI R.Multiple linear regression, support vector machines and neural networks for prediction of commercial building energy consumption[C]//International Hvac & R Congress and Exhibition.Serbia:Zbornik Meunarodnog Kongresa O KGH,2017:383-393.
[8] FUMO N,BISWAS M R.Regression analysis for prediction of residential energy consumption[J].Renewable Sustainable Energy Reviews,2015,47:332-343.DOI:10.1016/j.rser.2015.03.035.
[9] VEERAMSETTY V,MOHNOT A,SINGAL G,et al.Short term active power load prediction on a 33/11 kV substation using regression models[J].Energies,2021,14(11):2981.DOI:10.3390/en14112981.
[10] YANG Yunchun,YUAN Jiaqi,XIAO Ziwei,et al.Energy consumption characteristics and adaptive electricity pricing strategies for college dormitories based on historical monitored data[J].Energy Buildings,2021,245:111041.DOI:10.1016/j.enbuild.2021.111041.
[11] ARANDA A,FERREIRA G,MAINAR-TOLEDO M D,et al.Multiple regression models to predict the annual energy consumption in the Spanish banking sector[J].Energy Buildings,2012,49:380-387.DOI:10.1016/j.enbuild.2012.02.040.
[12] 孙晴,李明海,鲁娟,等.基于多元线性回归方法的高校宿舍建筑能耗分析[J].西安建筑科技大学学报(自然科学版),2018,50(6):919-924.DOI:10.15986/j.1006-7930.2018.06.024.
[13] YANG Hao,RAN Maoyu,ZENG Pengyaun.Patterns and influencing factors analysis of electricity consumption in university dormitories based on balance point temperatures[J].Building and Environment,2022,228:109679.DOI:10.1016/j.buildenv.2022.109679.
[14] BRAUN M R,ALTAN H,BECK S.Using regression analysis to predict the future energy consumption of a supermarket in the UK[J].Applied Energy,2014,130:305-313.DOI:10.1016/j.apenergy.2014.05.062.
[15] NIU Fuxin,O’NEILL Z,O’NEILL C.Data-driven based estimation of HVAC energy consumption using an improved Fourier series decomposition in buildings[J].Building Simulation,2018,11:633-645.DOI:10.1007/s12273-018-0431-2.
[16] 厦门历史天气预报查询[EB/OL].(2020-11-25)[2022-10-25] .http://www.tianqihoubao.com/lishi/xiamen.html.
[17] DING Yan,ZHANG Zhenqin,ZHANG Qiang,et al.Benchmark analysis of electricity consumption for complex campus buildings in China[J].Applied Thermal Engineering,2018,131:428-436.DOI:10.1016/j.applthermaleng.2017.12.024.
[18] DENG Yujing,GOU Zhonghua,GUI Xuechen,et al.Energy consumption characteristics and influential use behaviors in university dormitory buildings in China’s hot summer-cold winter climate region[J].Journal of Building Engineering,2021,33:101870.DOI:10.1016/j.jobe.2020.101870.
[19] WANG Jiayuan,ZHU Jiaolan,DING Zhikun,et al.Typical energy-related behaviors and gender difference for cooling energy consumption[J].Journal of Cleaner Production,2019,238:117846.DOI:10.1016/j.jclepro.2019.117846.
[20] 国务院办公厅.国务院办公厅关于2021年部分节假日安排的通知[EB/OL].(2020-11-25)[2022-10-25] .http://www.gov.cn/zhengce/content/2020-11/25/content_5564127.htm.
[21] VERICHEV K,ZAMORANO M,CARPIO M.Effects of climate change on variations in climatic zones and heating energy consumption of residential buildings in the southern Chile[J].Energy Buildings,2020,215:109874.DOI:10.1016/j.enbuild.2020.109874.
[22] XIANG Cao,TIAN Zhe.Impact of climate change on building heating energy consumption in Tianjin[J].Frontiers in Energy,2013,7(4):518-524.DOI:10.1007/s11708-013-0261-y.
[23] WANG Jiayuan,ZHU Jiaolan,DING Zhikun,et al.Typical energy-related behaviors and gender difference for cooling energy consumption[J].Journal of Cleaner Production,2019,238:117846.DOI:10.1016/j.jclepro.2019.117846.
[24] ASHRAE.ASHRAE guideline 14: Measurement of energy, demand, and water savings[M].Atlanta:American Society of Heating,Refrigerating,and Air-Conditioning Engineers,2014.

相似文献/References:

[1]秦旋,刘倩昆.厦门市公共建筑能耗影响因素与节能潜力分析[J].华侨大学学报(自然科学版),2015,36(5):575.[doi:10.11830/ISSN.1000-5013.2015.05.0575]
　QIN Xuan,LIU Qian-kun.Study on the Influencing Factors and Energy-Saving Potential of Energy Consumption of Public Building in Xiamen City[J].Journal of Huaqiao University(Natural Science),2015,36(2):575.[doi:10.11830/ISSN.1000-5013.2015.05.0575]

备注/Memo

备注/Memo:
收稿日期: 2022-11-09
通信作者: 冉茂宇(1967-),男,博士,教授,主要从事建筑室内外物理环境、建筑节能与建筑热工的研究.E-mail:ranmaoyu@hqu.edu.cn.
基金项目: 国家自然科学基金资助项目(51678254)
更新日期/Last Update: 2023-03-20