Forecasting model of building energy consumption based on parallel Kriging sampling algorithm

被引:0
|
作者
Zhao, Dongfang [1 ,2 ]
You, Xue-yi [1 ]
机构
[1] Tianjin Univ, Sch Environm Sci & Engn, Tianjin Key Lab Indoor Air Environm Qual Control, Tianjin 300350, Peoples R China
[2] Tianjin Chengjian Univ, Sch Energy & Safety Engn, Tianjin 300384, Peoples R China
关键词
Parallel sampling approach; Expected improvement; Kriging model; Energy consumption; ARTIFICIAL-INTELLIGENCE; OPTIMIZATION; PREDICTION; NETWORK;
D O I
10.1016/j.seta.2024.103676
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Parallel Kriging sampling approach (PEIGF) with minimum computing resources is proposed to promote the speed of building energy consumption. In each iteration of PEIGF, the initial sample point is obtained by maximizing the standard expected improvement global fit (EIGF) criterion and the parallel EIGF function is constructed to obtain multiple new sample points by maximizing the PEIGF criterion. Performance of PEIGF is evaluated by comparing the obtained results with four other existing sequence approaches and four artificial intelligence (AI) based models. The results reveal that PEIGF stands out for most of the test cases with good predictive accuracy and computing efficiency. PEIGF runs 4.7-11.6 times, 5.1-12.4 times, 5.0-14.8 times, and 19.7-158.6 times faster than those of combined expectation (CE), EIGF, expected improvement for global fit based on gradient (EIGFG) and maximum mean square error (MMSE) sampling. It obtains the least root mean squared errors for energy consumption prediction, and reduces the total number of samples by 14.9% (heating load) and 14.1% (cooling load), as well as 16.7% compared with other four AI-based models. It is proven to be a promising technique to plan low-cost energy management and facilitate early designs or renovation of energy conserving buildings.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Digital Twinning and ANN-based Forecasting Model for Building Energy Consumption
    Al-Mufti, Omar Ahmed
    Al-Isawi, Omar Adil
    Amirah, Lutfi Hatem
    Ghenai, Chaouki
    [J]. 2023 Advances in Science and Engineering Technology International Conferences, ASET 2023, 2023,
  • [2] Comparison of parallel infill sampling criteria based on Kriging surrogate model
    Cong Chen
    Jiaxin Liu
    Pingfei Xu
    [J]. Scientific Reports, 12
  • [3] Design of building energy consumption monitoring model based on parallel cloud computing
    Sun, Xiaoju
    [J]. INTERNATIONAL JOURNAL OF GLOBAL ENERGY ISSUES, 2020, 42 (5-6) : 457 - 469
  • [4] Comparison of parallel infill sampling criteria based on Kriging surrogate model
    Chen, Cong
    Liu, Jiaxin
    Xu, Pingfei
    [J]. SCIENTIFIC REPORTS, 2022, 12 (01)
  • [5] Forecasting the Building Energy Consumption in China Using Grey Model
    Dun, Meng
    Wu, Lifeng
    [J]. ENVIRONMENTAL PROCESSES-AN INTERNATIONAL JOURNAL, 2020, 7 (03): : 1009 - 1022
  • [6] Highly accurate energy consumption forecasting model based on parallel LSTM neural networks
    Jin, Ning
    Yang, Fan
    Mo, Yuchang
    Zeng, Yongkang
    Zhou, Xiaokang
    Yan, Ke
    Ma, Xiang
    [J]. Advanced Engineering Informatics, 2022, 51
  • [7] Forecasting the Building Energy Consumption in China Using Grey Model
    Meng Dun
    Lifeng Wu
    [J]. Environmental Processes, 2020, 7 : 1009 - 1022
  • [8] Deep Learning Model for Forecasting Institutional Building Energy Consumption
    Mlangeni, Simangaliso
    Ezugwu, Absalom E.
    Chiroma, Haruna
    [J]. 2020 CONFERENCE ON INFORMATION COMMUNICATIONS TECHNOLOGY AND SOCIETY (ICTAS), 2020,
  • [9] Energy Consumption Forecasting for the Digital-Twin Model of the Building
    Henzel, Joanna
    Wrobel, Lukasz
    Fice, Marcin
    Sikora, Marek
    [J]. ENERGIES, 2022, 15 (12)
  • [10] Highly accurate energy consumption forecasting model based on parallel LSTM neural networks
    Jin, Ning
    Yang, Fan
    Mo, Yuchang
    Zeng, Yongkang
    Zhou, Xiaokang
    Yan, Ke
    Ma, Xiang
    [J]. ADVANCED ENGINEERING INFORMATICS, 2022, 51