Predicting Energy Consumption in Building Heating Systems Using Model Identification Methods

Qu Minglu; Du Shanghe; Zhang Xinlin; Yu Zhen; Li Huai

doi:10.12465/j.issn.0253-4339.2025.03.145

您当前的位置：

首页 >

文章列表页 >

Predicting Energy Consumption in Building Heating Systems Using Model Identification Methods

更新时间：2025-05-30

- Predicting Energy Consumption in Building Heating Systems Using Model Identification Methods
- Journal of Refrigeration Vol. 46, Issue 3, Pages: 145-150(2025)
- 作者机构：
  
  1.上海理工大学环境与建筑学院　上海　 200093
  2.中国建筑科学研究院有限公司　北京　 100013
- 作者简介：
  
  Qu Minglu, female, associate professor, master supervisor, School of Environment and Architecture, University of Shanghai for Science and Technology, 86-13795377789, E-mail: quminglu@126.com. Research fields: air-source heat pump, heat and mass transfer process of building equipment.
- 基金信息：
- DOI：10.12465/j.issn.0253-4339.2025.03.145
  CLC： TU833;TP181
- Received：30 July 2024，
  
  Revised：28 September 2024，
  
  Accepted：17 October 2024，
  
  Published：16 June 2025
- 稿件说明：
移动端阅览
Qu Minglu, Du Shanghe, Zhang Xinlin, et al. Predicting Energy Consumption in Building Heating Systems Using Model Identification Methods[J]. Journal of refrigeration, 2025, 46(3): 145-150.
DOI：

Qu Minglu, Du Shanghe, Zhang Xinlin, et al. Predicting Energy Consumption in Building Heating Systems Using Model Identification Methods[J]. Journal of refrigeration, 2025, 46(3): 145-150. DOI： 10.12465/j.issn.0253-4339.2025.03.145.

摘要

利用机器学习技术深入分析楼宇产生的时间序列历史数据，基于黑箱模型竞争寻优的算法，开发了一种通用的模型辨识方法，通过多项式回归、人工神经网络、极端梯度提升3种机器学习方法竞争寻优确定最终的辨识模型。以北京市某近零能耗办公建筑为研究对象，基于建筑历史数据和TRNSYS供暖系统仿真模型数据，通过开发的模型辨识方法建立了建筑的负荷预测模型和设备能耗模型，在部署期间预测

值和总能耗误差值分别为0.87和5.18%。通过该模型辨识方法建立的预测模型精度较高，为后续系统能耗优化提供可靠依据。

Abstract

This study utilizes machine learning techniques to conduct an in-depth analysis of time-series historical data on energy consumption in buildings. A generalized model identification method was developed using an optimization algorithm based on black-box models. The final identification model was determined after optimizing three machine learning methods

including polynomial regression

artificial neural networks

and extreme gradient boosting. A near-zero energy office building in Beijing is the primary focus of this study. Using historical building data and simulation data of the heating system in TRNSYS

load prediction and equipment energy consumption models were established using the developed model identification method. During deployment

the predicted

valu

e and total energy consumption deviation were 0.87 and 5.18%

respectively. The results demonstrate that the prediction models established through this method possess high accuracy

providing a reliable basis for subsequent system energy consumption optimization.

关键词

Keywords

references

FASIUDDIN M , BUDAIWI I . HVAC system strategies for energy conservation in commercial buildings in Saudi Arabia [J ] . Energy and Buildings , 2011 , 43 ( 12 ): 3457 - 3466 .

沈泽南 . “双碳”目标下近零能耗建筑的节能性探索 [J ] . 新型建筑材料 , 2022 ( 8 ): 49 .

( SHEN Zenan . Exploration on energy conservation of near zero energy consumption buildings under the goal of "carbon peaking and carbon neutrality" [J ] . New Building Materials , 2022 ( 8 ): 49 .)

程程 , 姜益强 , 王菲 . 适用于近零能耗建筑的新型太阳能-污水源热泵系统运行特性 [J ] . 制冷学报 , 2022 , 43 ( 3 ): 142 - 149 .

( CHENG Cheng , JIANG Yiqiang , WANG Fei . Continuous operation analysis of new solar sewage dual-source heat pump for nearly zero-energy buildings [J ] . Journal of Refrigeration , 2022 , 43 ( 3 ): 142 - 149 .)

AFRAM A , JANABI-SHARIFI F . Black-box modeling of residential HVAC system and comparison of gray-box and black-box modeling methods [J ] . Energy and Buildings , 2015 , 94 : 121 - 149 .

AFRAM A , JANABI-SHARIFI F . Theory and applications of HVAC control systems-a review of model predictive control (MPC) [J ] . Building and Environment , 2014 , 72 : 343 - 355 .

RAFE BISWAS M A , ROBINSON M D , FUMO N . Prediction of residential building energy consumption: a neural network approach [J ] . Energy , 2016 , 117 : 84 - 92 .

ABBASIMEHR H , PAKI R , BAHRINI A . A novel XGBoost-based featurization approach to forecast renewable energy consumption with deep learning models [J ] . Sustainable Computing: Informatics and Systems , 2023 , 38 : 100863 .

LIU Yang , CHEN Hongyu , ZHANG Limao , et al . Energy consumption prediction and diagnosis of public buildings based on support vector machine learning: a case study in China [J ] . Journal of Cleaner Production , 2020 , 272 : 122542 .

ALAWADI S , MERA D , FERNÁNDEZ-DELGADO M , et al . A comparison of machine learning algorithms for forecasting indoor temperature in smart buildings [J ] . Energy Systems , 2022 , 13 ( 3 ): 689 - 705 .

王芸 , 端木琳 , 李祥立 , 等 . 独立双埋管太阳能辅助土壤源热泵系统模型建立与影响因素分析 [J ] . 制冷学报 , 2022 , 43 ( 3 ): 121 - 132 .

( WANG Yun , DUANMU Lin , LI Xiangli , et al . Model and parametric analysis of solar-assisted ground-source heat pump system with dual independently buried tubes [J ] . Journal of Refrigeration , 2022 , 43 ( 3 ): 121 - 132 .)

TSAI C L , CHEN W , CHANG C S . Polynomial-Fourier series model for analyzing and predicting electricity consumption in buildings [J ] . Energy and Buildings , 2016 , 127 : 301 - 312 .

AFRAM A , JANABI-SHARIFI F , FUNG A S , et al . Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: a state of the art review and case study of a residential HVAC system [J ] . Energy and Buildings , 2017 , 141 : 96 - 113 .

CHEN T , GUESTRIN C . XGBoost: a scalable tree boosting system [C ] // Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining . San Francisco , 2016 .

FAYED H A , ATIYA A F . Speed up grid-search for parameter selection of support vector machines [J ] . Applied Soft Computing , 2019 , 80 : 202 - 210 .

刘澄宁 , 梁星宇 , 邵亮亮 , 等 . 基于随机负荷预测的热泵热水系统节能运行策略优化 [J ] . 制冷学报 , 2023 , 44 ( 6 ): 36 - 42 .

( LIU Chengning , LIANG Xingyu , SHAO Liangliang , et al . Optimization of energy-saving operation strategy of heat pump hot-water system using stochastic load prediction [J ] . Journal of Refrigeration , 2023 , 44 ( 6 ): 36 - 42 .)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Energy Consumption Prediction of Building Heating Systems Based on Model Identification Methods

Practice and Optimization of Seasonal/Daily Composite Thermal Energy Storage Technology Based on Lakes/Rivers

Performance Simulation of a Solar Assisted Desiccant Wheel and Adsorption Cooling System

Practice and Optimization of Seasonal/Daily Composite Thermal Energy Storage Technology Based on Lakes/Rivers

Performance Simulation of a Solar Assisted Desiccant Wheel and Adsorption Cooling System

Related Author

李怀

于震

张欣林

杜尚赫

曲明璐

Cui Mengying

Yang Shuchuan

Yin Yonggao

Related Institution

中国建筑科学研究院有限公司

上海理工大学环境与建筑学院

Hebei Zhuopai Renewable Energy Development Co., Ltd.

School of Energy and Environment, Southeast University

Guangzhou Institute of Energy Conversion, Chinese Academy of Sciences

Address：10/F, Yindu Mansion, 67 Fucheng Road, Haidian Dist, Beijing, China Postal code：100142
Tel：010-68711412 Email：editor@car.org.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰