基于机器学习的建筑能耗研究进展
Advances in the Study of Building Energy Consumption by Machine Learning Method
DOI: 10.12677/CSA.2020.105103, PDF,   
作者: 李继伟, 徐 丽*：沈阳建筑大学市政与环境工程学院，辽宁 沈阳
关键词: 机器学习；建筑能耗；公共建筑；住宅建筑；Machine Learning； Building Energy Consumption； Public Building； Residential Building
摘要: 为了高效降低建筑能耗，减少碳排放，对采用机器学习算法进行建筑能耗研究进行了综述。首先介绍了机器学习的基本原理，然后介绍了基于机器学习方法的建筑能耗数据处理，最后介绍了基于机器学习方法的公共建筑、住宅建筑和建筑群能耗研究现状，并指出目前研究存在的问题及改进措施，提出今后尚需进一步研究的问题。
Abstract: In order to efficiently reduce building energy consumption and reduce carbon emissions, a review of building energy consumption research using machine learning algorithms is reviewed. First, the basic principles of machine learning are introduced, then building energy consumption data processing based on machine learning methods, and finally, the current status of research on energy consumption of public buildings, residential buildings and building groups based on machine learning methods. Several problems on the current research are pointed out. The proposals that need further study in the future are put forward.
文章引用：李继伟, 徐丽. 基于机器学习的建筑能耗研究进展[J]. 计算机科学与应用, 2020, 10(5): 1002-1008. https://doi.org/10.12677/CSA.2020.105103

参考文献

[1] Department of Climate Change (2015) Enhanced Actions of Climate Change: China’s Intended Nationally Determined Contributions. National Development & Reform Commission of China. http://www4.unfccc.int/submissions/indc/Submission%20Pages/submissions.aspx
[2] 孙弘历, 林波荣, 王者, 林智荣. 成都地区居住建筑不同供暖末端能耗与满意率调研[J]. 暖通空调, 2018, 48(2): 30-34+96.
[3] Chen, S., Li, N., Yoshino, H., Guan, J. and Levine, M.D. (2011) Statistical Analyses on Winter Energy Consumption Characteristics of Residential Buildings in Some Cities of China. Energy and Buildings, 43, 1063-1070. [Google Scholar] [CrossRef] 
[4] 柴盼, 刘旭, 翁庙成, 刘方. 重庆某住宅小区能耗特征与节能潜力研究[J]. 制冷与空调(四川), 2014(6): 694-697.
[5] Chen, J., Wang, X. and Steemers, K. (2013) A Statistical Analysis of a Residential Energy Consumption Survey Study in Hangzhou, China. Energy and Buildings, 66, 193-202. [Google Scholar] [CrossRef] 
[6] 唐峰, 王晓磊, 罗一哲, 周琪. 夏热冬冷地区住宅建筑能耗长期测试及使用行为模拟分析[J]. 建筑节能, 2016, 44(4): 104-107.
[7] 余晓平, 付祥钊, 廖小烽. 浅析夏热冬冷地区低能耗住宅技术路线[J]. 重庆建筑大学学报, 2008, 30(6): 116-119, 45.
[8] 邱童, 徐强, 王博, 胡立峰. 夏热冬冷地区城镇居住建筑能耗水平分析[J]. 建筑科学, 2013, 29(6): 23-26.
[9] D’hulstr, Labeeuw, W., Beusen, B., et al. (2015) Demand Response Flexibility and Flexibility Potential of Residential Smart Appliances: Experiences from Large Pilot Test in Belgium. Applied Energy, 155, 79-90. [Google Scholar] [CrossRef] 
[10] 高钢烽. 夏热冬冷地区住宅节能改造能耗模拟分析[J]. 低温建筑技术, 2009(10): 115-117.
[11] 刘倩, 张旭. 上海某住宅建筑围护结构能耗模拟与节能性分析[J]. 建筑科学, 2007(12): 24-26, 38.
[12] 刘祥, 邱烷南, 张华玲. 重庆地区现有居住实态下住宅的能耗研究[J]. 制冷与空调(四川), 2014(6): 623-627.
[13] 肖书博, 李念平. 夏热冬冷地区节能建筑能耗模拟与实测数据对比分析[C]//全国暖通空调制冷2010年学术年会. 杭州, 2010: 295.
[14] 袁玥. 基于机器学习的办公建筑暖通空调系统能耗预测及优化调度[D]: [硕士学位论文]. 武汉: 华中科技大学, 2019.
[15] 高庆龙, 杨柳, 刘加平, 冯雅. 居住建筑外墙传热系数优化研究[J]. 四川建筑科学研究, 2009, 35(1): 245-248.
[16] 唐鸣放, 窦枚, 王科. 重庆旧居住区建筑节能改造技术方案及效果分析[J]. 建筑技术, 2011, 42(10): 939-941.
[17] 高英博, 顾中煊, 罗淑湘, 等. 能耗预测导向的建筑能耗异常数据识别与修复[J]. 科学技术与工程, 2019, 19(35): 298-304.
[18] 吴蔚沁. 基于机器学习算法的建筑能耗监测数据异常识别及修复方法[J]. 建设科技, 2017(9): 60-62.
[19] 崔治国, 曹勇, 武根峰, 刘辉, 仇志飞, 陈传玮. 基于机器学习算法的建筑能耗监测数据预处理技术研究[J]. 建筑科学, 2018, 34(2): 94-99.
[20] 肖赋, 范成, 王盛卫. 基于数据挖掘技术的建筑系统性能诊断和优化[J]. 化工学报, 2014, 65(S2): 181-187.
[21] 杨石, 罗淑湘, 杜明. 基于数据挖掘的公共建筑能耗监管平台数据处理方法[J]. 暖通空调, 2015, 45(2): 82-86.
[22] 谢宜鑫. 基于机器学习的建筑空调能耗数据挖掘和模式识别[D]: [硕士学位论文]. 北京: 北京交通大学, 2019.
[23] 田玮, 魏来, 李占勇, 孟庆新, 宋继田, 杨松. 基于机器学习的建筑能耗模型适用性研究[J]. 天津科技大学学报, 2016, 31(3): 54-59.
[24] 丁子祥. 基于机器学习方法的建筑能耗预测研究[D]: [硕士学位论文]. 济南: 山东建筑大学, 2018.
[25] Robinson, C., Dilkina, B., Hubbs, J., et al. (2017) Machine Learning Approaches for Estimating Commercial Building Energy Consumption. Applied Energy, 208, 889-904. [Google Scholar] [CrossRef] 
[26] Lam, J.C. and Li, D.H.W. (2003) Electricity Consumption Characteristics in Shopping Malls in Subtropical Climates. Energy Conversion and Management, 44, 1391-1398. [Google Scholar] [CrossRef] 
[27] 刘文凤. 数据挖掘在公共建筑能耗分析中的应用研究[D]: [博士学位论文]. 重庆: 重庆大学, 2010.
[28] 邬棋帆. 医院建筑能耗分析诊断模型研究[D]: [硕士学位论文]. 西安: 西安建筑科技大学, 2018.
[29] Javed, A., Larijani, H. and Wixted, A. (2018) Improving Energy Consumption of a Commercial Building with IoT and Machine Learning. IT Professional, 20, 30-38. [Google Scholar] [CrossRef] 
[30] Rahman, A., Srikumar, V. and Smith, A.D. (2018) Predicting Electricity Consumption for Commercial and Residential Buildings Using Deep Recurrent Neural Networks. Applied En-ergy, 212, 372-385. [Google Scholar] [CrossRef] 
[31] Deng, H.F., Fannon, D. and Eckelman, M.J. (2018) Predictive Modeling for US Commercial Building Energy Use: A Comparison of Existing Statistical and Machine Learning Algo-rithms Using CBECS Microdata. Energy and Buildings, 163, 34-43. [Google Scholar] [CrossRef] 
[32] Samir, T., Jessica, G. and Samuel, F. (2018) Gradient Boosting Machine for Modeling the Energy Consumption of Commercial Buildings. Energy and Buildings, 158, 1533-1543. [Google Scholar] [CrossRef] 
[33] Naji, S., Keivani, A., Shamshirband, S., et al. (2016) Estimating Building Energy Consumption Using Extreme Learning Machine Method. Energy, 97, 506-516. [Google Scholar] [CrossRef] 
[34] 程亚豪, 陈焕新, 王江宇. 基于机器学习的住宅能耗预测[J]. 制冷与空调, 2019, 19(5): 35-40.
[35] 李信仪. 居住建筑区域能耗模型研究[D]: [博士学位论文]. 重庆: 重庆大学, 2018.
[36] Vázquez-Canteli, J.R., Ulyanin, S., Kämpf, J., et al. (2019) Fusing Tensor Flow with Building Energy Sim-ulation for Intelligent Energy Management in Smart Cities. Sustainable Cities and Society, 45, 243-257. [Google Scholar] [CrossRef] 
[37] Bourhnane, S., et al. (2020) Machine Learning for Energy Con-sumption Prediction and Scheduling in Smart Buildings. SN Applied Sciences, 2, Article No. 297.
[38] Pham, A.-D., Ngo, N.-T., Truong, T.T.H., Huynh, N.-T. and Truong, N.-S. (2020) Predicting Energy Consumption in Multiple Build-ings Using Machine Learning for Improving Energy Efficiency and Sustainability. Journal of Cleaner Production, 260, Article ID: 121082. [Google Scholar] [CrossRef] 
[39] Zeng, A., Ho, H. and Yu, Y. (2020) Predic-tion of Building Electricity Usage Using Gaussian Process Regression. Journal of Building Engineering, 28, Article ID: 101054. [Google Scholar] [CrossRef]