Selection of building energy consumption prediction machine learning algorithms and parameter setting based on quality of samples

doi:10.11835/j.issn.1000-582X.2020.058

Home > Archive>Volume 45, Issue 5, 2022 >79-95. DOI:10.11835/j.issn.1000-582X.2020.058

Selection of building energy consumption prediction machine learning algorithms and parameter setting based on quality of samples
DOI:
                        10.11835/j.issn.1000-582X.2020.058
                    
CSTR:
                        [cstr]
                    
Author:
                        LIU GangLIU Gang
School of Architecture, Tianjin University, Tianjin 300072, P. R. China;Tianjin Key Laboratory of Architectural Physics and Environmental Technology, Tianjin University, Tianjin 300072, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
LI XiaoqianLI Xiaoqian
School of Architecture, Tianjin University, Tianjin 300072, P. R. China;Tianjin Key Laboratory of Architectural Physics and Environmental Technology, Tianjin University, Tianjin 300072, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site
HAN ZhenHAN Zhen
School of Architecture, Tianjin University, Tianjin 300072, P. R. China;Tianjin Key Laboratory of Architectural Physics and Environmental Technology, Tianjin University, Tianjin 300072, P. R. China
Find this author on All Journals
Find this author on BaiDu
Search for this author on this site

                    
Affiliation:
Clc Number:TU17
Fund Project:

Article

Figures

Metrics

Reference [29]

Cited by

Materials

Comments

Abstract:

Machine learning algorithms are playing a more important role in building energy consumption prediction during the conceptual design. The selection of the machine learning algorithms and parameter setting have become a focus in the field of building performance design. However, the algorithms and their parameters are usually determined by the principle of algorithms rather than the features of the training samples which also have an effect on the performance of algorithms. Therefore, a classification method based on the quality of training samples which is evaluated by sample size and sample distribution characteristics is proposed. The performance of different machine learning algorithms for different quality sample sets is tested, and algorithm selection and parameter setting strategies for different quality sample sets are formulated. The relationship between sample quality and algorithm performance is investigated to provide effective guidance for architects.

Key words:building energy consumption prediction;machine learning algorithm;characteristic of the sample distribution

Reference

[1] 中国城市科学研究会. 中国绿色建筑2017[M]. 北京:中国建筑工业出版社, 2017.Chinese Society for Urban Studies. China green building2017[M]. Beijing:China Architecture & Building Press,2017.(in Chinese)

[2] 李紫微, 林波荣, 陈洪钟. 建筑方案能耗快速预测方法研究综述[J]. 暖通空调, 2018,48(5):1-8.Li Z W, Lin B R, Chen H Z. Review of rapid prediction method of building energy consumption[J]. Journal of HV&AC, 2018,48(5):1-8.(in Chinese)

[3] Machairas V, Tsangrassoulis A, Axarli K. Algorithms for optimization of building design:A review[J]. Renewable and Sustainable Energy Reviews, 2014,31:101-112.

[4] Wang D, Tan D, Liu L. Particle swarm optimization algorithm:an overview[J]. Soft Computing, 2018,22(2):387-408.

[5] Yang C F, Li H J, Rezgui Y, et al. High throughput computing based distributed genetic algorithm for building energy consumption optimization[J]. Energy and Buildings, 2014, 76:92-101.

[6] Tuhus-dubrow D, Krarti M. Genetic-algorithm based approach to optimize building envelope design for residential buildings[J]. Building and Environment, 2010,45(7):1574-1581.

[7] Carvalho A M D, Prati r C. Improving kNN classification under unbalanced data. A New Geometric Oversampling Approach[J]. 2018, 1-6.

[8] Sadrawi M, Sun W Z, Ma h M, et al. Ensemble genetic fuzzy neuro model applied for the emergency medical service via unbalanced data evaluation[J]. Symmetry, 2018, 10(3):71.

[9] 陈圣灵, 沈思淇, 李东升. 基于样本权重更新的不平衡数据集成学习方法[J]. 计算机科学, 2018, 45(7):31-37.Chen S L, Shen S Q, Li D S. Ensemble learning method for imbalanced data based on sample weight updating[J]. Computer Science, 2018, 45(7):31-37.(in Chinese)

[10] 蒋林, 陈涛, 屈梁生. 训练样本质量对人工神经网络性能的影响[J]. 中国机械工程, 1997, (2):123.Jiang L, Chen T, Qu L S. The effect of training sample quality on the performance of artificial neural networks[J].China Mechanical Engineering, 1997, (2):123.(in Chinese)

[11] Tharwat A, Hassanien A E, Elnaghi B E. A BA-based algorithm for parameter optimization of Support Vector Machine[J]. Pattern Recognition Letters, 2017,93:13-22.

[12] Wu C, Tzeng G, Lin R. A Novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression[J]. Expert Systems with Applications, 2009,36(3):4725-4735.

[13] Ding S, Su C, Yu J. An optimizing BP neural network algorithm based on genetic algorithm[J]. Artificial Intelligence Review, 2011,36(2):153-162.

[14] Ren C, An N, Wang J, et al. Optimal parameters selection for BP neural network based on particle swarm optimization:A case study of wind speed forecasting[J]. Knowledge-Based Systems, 2014,56:226-239.

[15] Vapnik V N. Support vector method for function approximation, regression estimation, and signal processing[J]. Advanced Neural Information Processing System, 1996,9(6):281-287.

[16] Zhao H, Magoulès F. A review on the prediction of building energy consumption[J]. Renewable and Sustainable Energy Reviews, 2012,16(6):3586-3592.

[17] Gu B, Sheng V S, Wang Z, et al. Incremental learning for ν-Support vector regression[J]. Neural Networks, 2015,67:140-150.

[18] Ahmad A S, Hassan m Y, Abdullah M P, et al. A review on applications of ANN and SVM for building electrical energy consumption forecasting[J]. Renewable and Sustainable Energy Reviews, 2014,33:102-109.

[19] Dong B, Cao C, Lee S E. Applying support vector machines to predict building energy consumption in tropical region[J]. Energy and Buildings, 2005,37(5):545-553.

[20] Chou J, Bui D. Modeling heating and cooling loads by artificial intelligence for energy-efficient building design[J]. Energy and Buildings, 2014,82:437-446.

[21] Zhong H, Wang J, Jia H, et al. Vector field-based support vector regression for building energy consumption prediction[J]. Applied Energy, 2019,242:403-414.

[22] 刘彩红. BP神经网络学习算法的研究[D]. 重庆:重庆师范大学, 2008.Liu C H. The study of algorithm of BP neural network[D]. Chongqing:Chongqing Normal University, 2008.(in Chinese)

[23] Chen K, Jiang J, Zheng F, et al. A novel data-driven approach for residential electricity consumption prediction based on ensemble learning[J]. Energy, 2018,150:49-60.

[24] Wang Z, Wang Y, Srinivasan R S. A novel ensemble learning approach to support building energy use prediction[J]. Energy and Buildings, 2018,159:109-122.

[25] Papadopoulos S A E W W. Evaluation of tree-based ensemble learning algorithms for building energy performance estimation[J]. Journal of Building Performance Simulation, 2017,11(3):322-332.

[26] 王永明. 集成回归问题若干关键技术研究[D]. 上海:华东师范大学, 2015.Wang Y M. Research on some key technologies in ensemble regression problem[D]. Shanghai:East China Normal University, 2015.(in Chinese)

[27] Bauer E K R. An empirical comparison of voting classification algorithms:bagging, boosting, and variants[J]. Mach Learn, 1999,36(1-2):105-139.

[28] 梁礼明, 冯新刚, 陈云嫩, 等. 基于样本分布特征的核函数选择方法研究[J]. 计算机仿真, 2013,30(1):323-328.Lang L M, Feng X G, Chen Y N, et al., Method of selection kernel function based on distribution characteristics of samples[J]. Computer Simulation, 2013,30(1):323-328.(in Chinese)

[29] Zhou Z H W J X T. Ensembling neural networks:Many could be better than all[J]. Artif Intell, 2002,137(1/2):239-263.

Get Citation

刘刚,李晓倩,韩臻.基于样本集质量的建筑能耗预测机器学习算法选择及参数设置[J].重庆大学学报,2022,45(5):79~95

Copy

Article Metrics

Abstract:
PDF:
HTML:
Cited by:

History

Received:March 11,2020
Revised:
Adopted:
Online: June 11,2022
Published:

Home

Get Citation

Related Videos

Share

Article Metrics

History

Article QR Code