A Data-Driven Approach to Forecasting Heating and Cooling Energy Demand in an Office Building as an Alternative to Multi-Zone Dynamic Simulation

被引:5
|
作者
Godinho, Xavier [1 ,2 ]
Bernardo, Hermano [1 ,2 ]
de Sousa, Joao C. [1 ,2 ]
Oliveira, Filipe T. [1 ,2 ]
机构
[1] Polytech Leiria, Sch Technol & Management, P-2411901 Leiria, Portugal
[2] Univ Coimbra, Polo 2, DEEC, INESC Coimbra, P-3030790 Coimbra, Portugal
来源
APPLIED SCIENCES-BASEL | 2021年 / 11卷 / 04期
关键词
load forecasting; building energy demand; artificial neural networks; support vector machines; simulated annealing; data-driven methods; multi-zone dynamic simulation;
D O I
10.3390/app11041356
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Nowadays, as more data is now available from an increasing number of installed sensors, load forecasting applied to buildings is being increasingly explored. The amount and quality of resulting information can provide inputs for smarter decisions when managing and operating office buildings. In this article, the authors use two data-driven methods (artificial neural networks and support vector machines) to predict the heating and cooling energy demand in an office building located in Lisbon, Portugal. In the present case-study, these methods prove to be an accurate and appealing alternative to the use of accurate but time-consuming multi-zone dynamic simulation tools, which strongly depend on several parameters to be inserted and user expertise to calibrate the model. Artificial neural networks and support vector machines were developed and parametrized using historical data and different sets of exogenous variables to encounter the best performance combinations for both the heating and cooling periods of a year. In the case of support vector regression, a variation introduced simulated annealing to guide the search for different combinations of hyperparameters. After a feature selection stage for each individual method, the results for the different methods were compared, based on error metrics and distributions. The outputs of the study include the most suitable methodology for each season, and also the features (historical load records, but also exogenous features such as outdoor temperature, relative humidity or occupancy profile) that led to the most accurate models. Results clearly show there is a potential for faster, yet accurate machine-learning based forecasting methods to replace well-established, very accurate but time-consuming multi-zone dynamic simulation tools to forecast building energy consumption.
引用
收藏
页码:1 / 23
页数:23
相关论文
共 50 条
  • [31] Simultaneous Energy Optimization of Heating Systems by Multi-Zone Predictive Control—Application to a Residential Building
    Univ. Artois, IMT Nord Europe, Junia, Univ. Lille, ULR 4515, Laboratoire de Génie Civil et géo-Environnement , Béthune
    F-62400, France
    不详
    不详
    F-59000, France
    Buildings, 1600, 10
  • [32] A data-driven approach for the disaggregation of building-sector heating and cooling loads from hourly utility load data
    Hu, Yinbo
    Waite, Michael
    Patz, Evan
    Xia, Bainan
    Xu, Yixing
    Olsen, Daniel
    Gopan, Naveen
    Modi, Vijay
    ENERGY STRATEGY REVIEWS, 2023, 49
  • [33] A Supervised-Learning-Based Strategy for Optimal Demand Response of an HVAC System in a Multi-Zone Office Building
    Kim, Young-Jin
    IEEE TRANSACTIONS ON SMART GRID, 2020, 11 (05) : 4212 - 4226
  • [34] Stochastic RCM-driven cooling and heating energy demand analysis for residential building
    Tian, Chuyin
    Huang, Guohe
    Piwowar, Joseph M.
    Yeh, Shin-Cheng
    Lu, Chen
    Duan, Ruixin
    Ren, Jiayan
    RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2022, 153
  • [35] Modelling heating and cooling energy demand for building stock using a hybrid approach
    Li, Xinyi
    Yao, Runming
    ENERGY AND BUILDINGS, 2021, 235
  • [36] length A data-driven approach for fault diagnosis in multi-zone HVAC systems: Deep neural bilinear Koopman parity
    Irani, Fatemeh Negar
    Bakhtiaridoust, Mohammadhosein
    Yadegar, Meysam
    Meskin, Nader
    JOURNAL OF BUILDING ENGINEERING, 2023, 76
  • [37] Empirical validation of a data-driven heating demand simulation with error correction methods
    Bunning, Felix
    Bollinger, Andrew
    Heer, Philipp
    Smith, Roy S.
    Lygeros, John
    PROCEEDINGS OF BUILDING SIMULATION 2019: 16TH CONFERENCE OF IBPSA, 2020, : 1428 - 1435
  • [38] A Markov chain-based approach for assessing respiratory infection risk in a multi-zone office building
    Zhen, Qi
    Zhang, Anxiao
    Bokel, Regina
    Zheng, Yue
    Li, Jing
    Du, Yiming
    Zhang, Qi
    JOURNAL OF BUILDING ENGINEERING, 2024, 90
  • [39] Electric Vehicle Charging Demand Forecasting Model Based on Data-driven Approach
    Xing Q.
    Chen Z.
    Huang X.
    Zhang Z.
    Leng Z.
    Xu Y.
    Zhao Q.
    Zhongguo Dianji Gongcheng Xuebao/Proceedings of the Chinese Society of Electrical Engineering, 2020, 40 (12): : 3796 - 3812
  • [40] Model-based and Data-driven Anomaly Detection for Heating and Cooling Demands in Office Buildings
    Ashouri, Araz
    Hu, Yitian
    Gunay, H. Burak
    Newsham, Guy R.
    Shen, Weiming
    ASHRAE TRANSACTIONS 2019, VOL 125, PT 1, 2019, 125 : 87 - 95