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
  • [1] Data-driven short-term load forecasting for heating and cooling demand in office buildings
    Ashouri, Araz
    Shi, Zixiao
    Gunay, H. Burak
    CLIMATE RESILIENT CITIES - ENERGY EFFICIENCY & RENEWABLES IN THE DIGITAL ERA (CISBAT 2019), 2019, 1343
  • [2] Data-driven identification of a thermal network in multi-zone building
    Doddi, Harish
    Talukdar, Saurav
    Deka, Deepjyoti
    Salapaka, Murti
    2018 IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2018, : 7302 - 7307
  • [3] Data-Driven Fault-Tolerant Control for Energy Efficiency in a Multi-Zone Building
    Jain, Tushar
    Yame, Joseph J.
    Sauter, Dominique
    2016 14TH INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION, ROBOTICS AND VISION (ICARCV), 2016,
  • [4] Thermal Dynamic Modeling and Simulation of a Heating System for a Multi-Zone Office Building Equipped with Demand Controlled Ventilation Using MATLAB/Simulink
    Behravan, Ali
    Obermaisser, Roman
    Nasari, Amirbahador
    2017 INTERNATIONAL CONFERENCE ON CIRCUITS, SYSTEM AND SIMULATION (ICCSS 2017), 2017, : 103 - 108
  • [5] Energy Management Strategy for Zone Cooling Load Demand Reduction in Commercial Buildings: A Data-Driven Approach
    Kannan, Thirugnanam
    Lork, Clement
    Tushar, Wayes
    Yuen, Chau
    Wong, Ngian Chung
    Tai, Stewart
    Lan, Lan
    Wood, Kristin L.
    IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2019, 55 (06) : 7281 - 7299
  • [6] Short-term cooling and heating loads forecasting of building district energy system based on data-driven models
    Yu, Hanfei
    Zhong, Fan
    Du, Yuji
    Xie, Xiang'e
    Wang, Yibin
    Zhang, Xiaosong
    Huang, Shifang
    ENERGY AND BUILDINGS, 2023, 298
  • [7] A multi-zone building energy simulation of a data center model with hot and cold aisles
    Long Phan
    Lin, Cheng-Xian
    ENERGY AND BUILDINGS, 2014, 77 : 364 - 376
  • [8] A Multi-Zone Building Energy Simulation of a Data Center Model with Hot and Cold Aisles
    Phan, Long
    Lin, Cheng-Xian
    Schaefer, Mirko
    PROCEEDINGS OF THE ASME 7TH INTERNATIONAL CONFERENCE ON ENERGY SUSTAINABILITY, 2013, 2014,
  • [9] Evaluating data-driven building stock heat demand forecasting models for energy optimization
    Jafarinejad, Tohid
    De Jaeger, Ina
    Erfani, Arash
    Saelens, Dirk
    PROCEEDINGS OF BUILDING SIMULATION 2021: 17TH CONFERENCE OF IBPSA, 2022, 17 : 310 - 317
  • [10] Basket data-driven approach for omnichannel demand forecasting
    Omar, Haytham
    Klibi, Walid
    Babai, M. Zied
    Ducq, Yves
    INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2023, 257