多源数据建筑能耗预测及混合模型性能对比

万更新; 汪洋; 赵璐

doi:10.3724/j.gyjzG25060613

多源数据建筑能耗预测及混合模型性能对比

doi: 10.3724/j.gyjzG25060613

万更新¹,
汪洋^1, ,,
赵璐²

1. 武汉大学土木建筑工程学院, 武汉 430072;
2. 中交武汉智行国际工程咨询有限公司, 武汉 430011

基金项目:

湖北省重大攻关项目（JD）（2023BAA007）；武汉市城建局科技项目计划项目（202343）。

详细信息

作者简介:
万更新，硕士研究生，主要从事智能建造与管理研究。

通讯作者:
汪洋，博士，教授，主要从事智能建造与管理研究，wangyang.whu@foxmail.com。

计量
- 文章访问数: 14
- HTML全文浏览量: 6
- PDF下载量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2025-06-06
- 网络出版日期: 2026-11-07

Building Energy Consumption Prediction Driven by Multi-Source Data and Performance Comparison of Hybrid Models

WAN Gengxin¹,
WANG Yang^{1
, ,},
ZHAO Lu²

1. School of Civil Engineering, Wuhan University, Wuhan 430072, China;
2. CCCC Wuhan Zhixing International Engineering Consulting Co., Ltd., Wuhan 430011, China

摘要

摘要: 建筑能耗预测在提升建筑能效水平与降低运营成本方面发挥着关键作用，因此有效整合多源异构数据，运用深度学习技术构建准确可靠的能耗预测模型具有重要意义。研究采用基于最大信息系数和格兰杰因果检验的两阶段特征选择优化建筑能耗预测特征集，基于时间卷积网络（TCN）、门控循环单元（GRU）和注意力机制（Attention）构建了四种混合深度学习模型（TCN-GRU、TCN-Attention、GRU-Attention、TCN-GRU-Attention），利用五类建筑的多源动态数据集，从模型架构与数据规模两个维度对比分析其性能。研究结果表明，混合模型TCN-GRU的综合性能最佳，预测误差低于所有对比模型，验证了TCN擅长捕捉局部时序特征与GRU擅长学习长时依赖关系的互补优势。同时，通过实验发现相比于混合模型，TCN/GRU模型随数据规模扩展展现出更稳健的性能提升。
- 建筑能耗预测 /
- 特征工程 /
- 混合深度学习
Abstract: Building energy consumption prediction plays a critical role in improving energy efficiency and reducing operational costs. Effectively integrating multi-source heterogeneous data and leveraging deep learning techniques to develop accurate and reliable prediction models is of significant importance. This study employed a two-stage feature selection method based on the maximum information coefficient and Granger causality test to optimize the feature set for building energy consumption prediction. Subsequently， four hybrid deep learning models were constructed by combining temporal convolutional network （TCN）， gated recurrent unit （GRU）， and attention mechanism （Attention） in different architectures： TCN-GRU， TCN-Attention， GRU-Attention， and TCN-GRU-Attention. The performance of these models was then comparatively analyzed from both architectural and data-scale perspectives using multi-source dynamic datasets from five categories of buildings. The results demonstrated that the TCN-GRU hybrid model achieved the best overall performance， with prediction errors lower than all baseline models， validating the complementary strengths of TCN in capturing local temporal features and GRU in learning long-term dependencies. Additionally， experiments revealed that， compared to hybrid models， the TCN/GRU models exhibited more robust performance improvements as data volume increased.
- building energy consumption prediction /
- feature engineering /
- hybrid deep learning

HTML全文

参考文献(12)

[1]	蔡伟光,于艳辉,刘源. 中国城乡建设领域碳排放研究报告（2024年）[J]. 建筑,2025（2）:56-63.
[2]	MOHAMAD K,STEPHEN M A,ZOYA P,et al. Machine learning,deep learning,and statistical analysis for forecasting building energy consumption-a systematic review[J]. Engineering Applications of Artificial Intelligence,2022,115:105287.
[3]	WEI Y X,ZHANG X X,SHI Y,et al. A review of data-driven approaches for prediction and classification of building energy consumption[J]. Renewable& Sustainable Energy Reviews,2018,82:1027-1047.
[4]	HIMEUR Y,GHANEM K,ALSALEMI A,et al. Artificial intelligence based anomaly detection of energy consumption in buildings:a review,current trends and new perspectives[J]. Applied Energy,2021,287:116601.
[5]	AMASYALI K,EL-GOHARY N M. A review of data-driven building energy consumption prediction studies[J]. Renewable& Sustainable Energy Reviews,2018,81:1192-1205.
[6]	MILLER C,KATHIRGAMANATHAN A,PICCHETTI B,et al. The building data genome project 2,energy meter data from the ASHRAE Great Energy Predictor Ⅲ competition[J]. Scientific Data,2020,7（1）:368.
[7]	ZHANG L,WEN J. A systematic feature selection procedure for short-term data-driven building energy forecasting model development[J]. Energy and Buildings,2019,183:428-442.
[8]	WANG X,FANG F,ZHANG X,et al. LSTM-based short-term load forecasting for building electricity consumption[C]// Proceedings of the 2019 IEEE 28th International Symposium on Industrial Electronics（ISIE）. Paris:IEEE,2019:1-6.
[9]	XIE J,CHEN Y,HONG T,et al. Relative humidity for load forecasting models[J]. IEEE Transactions on Smart Grid,2018,9（1）:191-198.
[10]	MOON J,MAQSOOD M,SO D,et al. Advancing ensemble learning techniques for residential building electricity consumption forecasting:insight from explainable artificial intelligence[J]. PLOS One,2024,19（11）:e0307654.
[11]	KIM T Y,CHO S B. Predicting residential energy consumption using CNN-LSTM neural networks[J]. Energy,2019,182:72-81.
[12]	CHITALIA G,PIPATTANASOMPORN M,GARG V,et al. Robust short-term electrical load forecasting framework for commercial buildings using deep recurrent neural networks[J]. Applied Energy,2020,278:115410.