Physics-constrained graph modeling for building thermal dynamics

IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Energy and AI Pub Date : 2024-02-01 DOI:10.1016/j.egyai.2024.100346
Ziyao Yang , Amol D. Gaidhane , Ján Drgoňa , Vikas Chandan , Mahantesh M. Halappanavar , Frank Liu , Yu Cao
{"title":"Physics-constrained graph modeling for building thermal dynamics","authors":"Ziyao Yang ,&nbsp;Amol D. Gaidhane ,&nbsp;Ján Drgoňa ,&nbsp;Vikas Chandan ,&nbsp;Mahantesh M. Halappanavar ,&nbsp;Frank Liu ,&nbsp;Yu Cao","doi":"10.1016/j.egyai.2024.100346","DOIUrl":null,"url":null,"abstract":"<div><p>In this paper, we propose a graph model embedded with compact physical equations for modeling the thermal dynamics of buildings. The principles of heat flow across various components in the building, such as walls and doors, fit the message-passing strategy used by Graph Neural networks (GNNs). The proposed method is to represent the multi-zone building as a graph, in which only zones are considered as nodes, and any heat flow between zones is modeled as an edge based on prior knowledge of the building structure. Furthermore, the thermal dynamics of these components are described by compact models in the graph. GNNs are further employed to train model parameters from collected data. During model training, our proposed method enforces physical constraints (e.g., zone sizes and connections) on model parameters and propagates the penalty in the loss function of GNN. Such constraints are essential to ensure model robustness and interpretability. We evaluate the effectiveness of the proposed modeling approach on a realistic dataset with multiple zones. The results demonstrate a satisfactory accuracy in the prediction of multi-zone temperature. Moreover, we illustrate that the new model can reliably learn hidden physical parameters with incomplete data.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":null,"pages":null},"PeriodicalIF":9.6000,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000120/pdfft?md5=0e483d0c4e3f88c26fc90d4d25f20085&pid=1-s2.0-S2666546824000120-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy and AI","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2666546824000120","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

In this paper, we propose a graph model embedded with compact physical equations for modeling the thermal dynamics of buildings. The principles of heat flow across various components in the building, such as walls and doors, fit the message-passing strategy used by Graph Neural networks (GNNs). The proposed method is to represent the multi-zone building as a graph, in which only zones are considered as nodes, and any heat flow between zones is modeled as an edge based on prior knowledge of the building structure. Furthermore, the thermal dynamics of these components are described by compact models in the graph. GNNs are further employed to train model parameters from collected data. During model training, our proposed method enforces physical constraints (e.g., zone sizes and connections) on model parameters and propagates the penalty in the loss function of GNN. Such constraints are essential to ensure model robustness and interpretability. We evaluate the effectiveness of the proposed modeling approach on a realistic dataset with multiple zones. The results demonstrate a satisfactory accuracy in the prediction of multi-zone temperature. Moreover, we illustrate that the new model can reliably learn hidden physical parameters with incomplete data.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
建筑热动力学的物理约束图建模
在本文中,我们提出了一种内嵌紧凑物理方程的图形模型,用于模拟建筑物的热动态。建筑物内各部件(如墙壁和门)之间的热流原理符合图神经网络(GNN)所使用的信息传递策略。所提出的方法是将多分区建筑物表示为一个图,其中只将分区视为节点,分区之间的任何热流都将根据建筑物结构的先验知识建模为一条边。此外,这些组件的热动态由图中的紧凑模型来描述。我们进一步采用 GNN 从收集到的数据中训练模型参数。在模型训练过程中,我们提出的方法会对模型参数施加物理约束(如区域大小和连接),并在 GNN 的损失函数中传播惩罚。这些约束对于确保模型的稳健性和可解释性至关重要。我们在一个具有多个区域的现实数据集上评估了所提出的建模方法的有效性。结果表明,多区域温度预测的准确性令人满意。此外,我们还证明了新模型可以在数据不完整的情况下可靠地学习隐藏的物理参数。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Energy and AI
Energy and AI Engineering-Engineering (miscellaneous)
CiteScore
16.50
自引率
0.00%
发文量
64
审稿时长
56 days
期刊最新文献
Optimizing catalyst layer composition of PEM fuel cell via machine learning: Insights from in-house experimental data A novel optimization framework for natural gas transportation pipeline networks based on deep reinforcement learning Exploring public attention in the circular economy through topic modelling with twin hyperparameter optimisation Adaptive control systems for dual axis tracker using clear sky index and output power forecasting based on ML in overcast weather conditions Supporting energy policy research with large language models: A case study in wind energy siting ordinances
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1