The Cost-Optimal Control of Building Air Conditioner Loads Based on Machine Learning: A Case Study of an Office Building in Nanjing

被引:0
|
作者
Guo, Zhenwei [1 ,2 ]
Wang, Xinyu [2 ]
Wang, Yao [3 ,4 ]
Zhu, Fenglei [4 ]
Zhou, Haizhu [5 ]
Zhang, Miao [5 ]
Wang, Yuxiang [2 ]
机构
[1] State Key Lab Bldg Safety & Built Environm, Beijing 100013, Peoples R China
[2] Chinese Soc Urban Studies, Beijing, Peoples R China
[3] Tsinghua Univ, Sch Architecture, Beijing 100190, Peoples R China
[4] Beijing Glory PKPM Technol Co Ltd, Beijing 100013, Peoples R China
[5] China Acad Bldg Res, Beijing 100013, Peoples R China
关键词
building air conditioner load; machine learning; load control; energy costs; indoor temperature; ENERGY-CONSUMPTION; FAULT-DIAGNOSIS; DEMAND RESPONSE; RESERVE MARKET; COOLING SYSTEM; HVAC SYSTEM; PREDICTION; MODEL;
D O I
10.3390/buildings14103040
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
Building envelopes and indoor environments exhibit thermal inertia, forming a virtual energy storage system in conjunction with the building air conditioner (AC) system. This system represents a current demand response resource for building electricity use. Thus, this study centers on the CatBoost algorithm within machine learning (ML) technology, utilizing the LASSO regression model for feature selection and applying the Optuna framework for hyperparameter optimization (HPO) to develop a cost-optimal control method for minimizing building AC loads. This method addresses the challenges associated with traditional load forecasting and control methods, which are often impacted by environmental temperature, building parameters, and user behavior uncertainties. These methods struggle to accurately capture the complex dynamics and nonlinear relationships of AC operations, making it difficult to devise AC operation and virtual energy storage scheduling strategies effectively. The proposed method was applied and validated using a case study of an office building in Nanjing, China. The prediction results showed coefficient of variation in root mean square error (CV-RMSE) values of 6.4% and 2.2%. Compared with the original operating conditions, the indoor temperature remained within a comfortable range, the AC load was reduced by 5.25%, and the operating energy costs were reduced by 24.94%. These results demonstrate that the proposed method offers improved computational efficiency, enhanced model performance, and economic benefits.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] A machine learning-based framework for cost-optimal building retrofit
    Deb, Chirag
    Dai, Zhonghao
    Schlueter, Arno
    APPLIED ENERGY, 2021, 294
  • [2] Machine Learning Approach to Predict Building Thermal Load Considering Feature Variable Dimensions: An Office Building Case Study
    Chen, Yongbao
    Ye, Yunyang
    Liu, Jingnan
    Zhang, Lixin
    Li, Weilin
    Mohtaram, Soheil
    BUILDINGS, 2023, 13 (02)
  • [3] Design the refurbishment of historic buildings with the cost-optimal methodology: The case study of a XV century Italian building
    Ascione, Fabrizio
    Cheche, Nicla
    De Masi, Rosa Francesca
    Minichiello, Francesco
    Vanoli, Giuseppe Peter
    ENERGY AND BUILDINGS, 2015, 99 : 162 - 176
  • [4] Evaluation of the optimal thermal insulation thickness for an office building in different climates by means of the basic and modified "cost-optimal" methodology
    D'Agostino, Diana
    de' Rossi, Filippo
    Marigliano, Marcello
    Marino, Concetta
    Minichiello, Francesco
    JOURNAL OF BUILDING ENGINEERING, 2019, 24
  • [5] Modelling Office Building Rent Prediction based on Auto Model in Machine Learning
    Mohd, Thuraiya
    Harussani, Muhamad
    Masrom, Suraya
    Johari, Noraini
    Alfat, Lathifah
    ENVIRONMENT-BEHAVIOUR PROCEEDINGS JOURNAL, 2022, 7 (19):
  • [6] Advances in Machine-Learning Based Disaggregation of Building Heating Loads: A Review
    Lien, Synne Krekling
    Najafi, Behzad
    Rajasekharan, Jayaprakash
    ENERGY INFORMATICS, EI.A 2023, PT I, 2024, 14467 : 179 - 201
  • [7] Energy Optimal Control of a Multivalent Building Energy System using Machine Learning
    Huang, Chenzi
    Seidel, Stephan
    Jia, Xuehua
    Paschke, Fabian
    Braeunig, Jan
    PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON SMART CITIES AND GREEN ICT SYSTEMS (SMARTGREENS), 2021, : 57 - 66
  • [8] Energy consumption prediction by using machine learning for smart building: Case study in Malaysia
    Shapi, Mel Keytingan M.
    Ramli, Nor Azuana
    Awalin, Lilik J.
    DEVELOPMENTS IN THE BUILT ENVIRONMENT, 2021, 5
  • [9] Supervisory optimal control using machine learning for building thermal comfort
    Abdufattokhov, Shokhjakhon
    Mahamatov, Nurilla
    Ibragimova, Kamila
    Gulyamova, Dilfuza
    Yuldashev, Dilyorjon
    OPERATIONS RESEARCH AND DECISIONS, 2022, 32 (04) : 1 - 15
  • [10] An Innovative Modelling Approach Based on Building Physics and Machine Learning for the Prediction of Indoor Thermal Comfort in an Office Building
    Tardioli, Giovanni
    Filho, Ricardo
    Bernaud, Pierre
    Ntimos, Dimitrios
    BUILDINGS, 2022, 12 (04)