Data-driven building energy efficiency prediction using physics-informed neural networks

被引:1
|
作者
Michalakopoulos, Vasilis [1 ]
Pelekis, Sotiris [1 ]
Kormpakis, Giorgos [1 ]
Karakolis, Vagelis [1 ]
Mouzakitis, Spiros [1 ]
Askounis, Dimitris [1 ]
机构
[1] Natl Tech Univ Athens, Sch Elect & Comp Engn, Decis Support Syst Lab, Athens, Greece
关键词
Deep learning; Physics-informed; Energy audit; Residential buildings; Building energy efficiency; Energy performance prediction;
D O I
10.1109/SusTech60925.2024.10553513
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The analytical prediction of building energy performance in residential buildings based on the heat losses of its individual envelope components is a challenging task. It is worth noting that this field is still in its infancy, with relatively limited research conducted in this specific area to date, especially when it comes for data-driven approaches. In this paper we introduce a novel physics-informed neural network model for addressing this problem. Through the employment of unexposed datasets that encompass general building information, audited characteristics, and heating energy consumption, we feed the deep learning model with general building information, while the model's output consists of the structural components and several thermal properties that are in fact the basic elements of an energy performance certificate (EPC). On top of this neural network, a function, based on physics equations, calculates the energy consumption of the building based on heat losses and enhances the loss function of the deep learning model. This methodology is tested on a real case study for 256 buildings located in Riga, Latvia. Our investigation comes up with promising results in terms of prediction accuracy, paving the way for automated, and data-driven energy efficiency performance prediction based on basic properties of the building, contrary to exhaustive energy efficiency audits led by humans, which are the current status quo.
引用
收藏
页码:84 / 91
页数:8
相关论文
共 50 条
  • [1] Data-driven modeling of Landau damping by physics-informed neural networks
    Qin, Yilan
    Ma, Jiayu
    Jiang, Mingle
    Dong, Chuanfei
    Fu, Haiyang
    Wang, Liang
    Cheng, Wenjie
    Jin, Yaqiu
    [J]. PHYSICAL REVIEW RESEARCH, 2023, 5 (03):
  • [2] Data-driven physics-informed neural networks: A digital twin perspective
    Yang, Sunwoong
    Kim, Hojin
    Hong, Yoonpyo
    Yee, Kwanjung
    Maulik, Romit
    Kang, Namwoo
    [J]. COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING, 2024, 428
  • [3] Data-driven discovery of turbulent flow equations using physics-informed neural networks
    Yazdani, Shirindokht
    Tahani, Mojtaba
    [J]. PHYSICS OF FLUIDS, 2024, 36 (03)
  • [4] Physics-informed neural networks for data-driven simulation: Advantages, limitations, and opportunities
    de la Mata, Felix Fernandez
    Gijon, Alfonso
    Molina-Solana, Miguel
    Gomez-Romero, Juan
    [J]. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2023, 610
  • [5] Development of a data-driven simulation framework using physics-informed neural network
    Chae, Young Ho
    Kim, Hyeonmin
    Bang, Jungjin
    Seong, Poong Hyun
    [J]. ANNALS OF NUCLEAR ENERGY, 2023, 189
  • [6] Physics-informed Data-driven Communication Performance Prediction for Underwater Vehicles
    Chitre, Mandar
    Li Kexin
    [J]. 2022 SIXTH UNDERWATER COMMUNICATIONS AND NETWORKING CONFERENCE (UCOMMS), 2022,
  • [8] Data-driven soliton solution implementation based on nonlinear adaptive physics-informed neural networks
    Zhang, Jianlin
    Leng, Yake
    Wu, Chaofan
    Su, Chaoyuan
    [J]. NONLINEAR DYNAMICS, 2024, : 1467 - 1488
  • [9] Comparison of Data-Driven and Physics-Informed Neural Networks for Surrogate Modelling of the Huxley Muscle Model
    Milicevic, Bogdan
    Ivanovic, Milos
    Stojanovic, Boban
    Milosevic, Miljan
    Simic, Vladimir
    Kojic, Milos
    Filipovic, Nenad
    [J]. APPLIED ARTIFICIAL INTELLIGENCE 2: MEDICINE, BIOLOGY, CHEMISTRY, FINANCIAL, GAMES, ENGINEERING, SICAAI 2023, 2024, 999 : 33 - 37
  • [10] Multifidelity deep operator networks for data-driven and physics-informed problems
    Howard A.A.
    Perego M.
    Karniadakis G.E.
    Stinis P.
    [J]. Journal of Computational Physics, 2023, 493