引用本文:付伟豪,赵千川.基于TCN-LSTM-Attention的建筑热动态与能耗预测[J].控制理论与应用,2025,42(11):2125~2135.[点击复制]
FU Wei-hao,ZHAO Qian-chuan.Thermal dynamics and energy consumption prediction of buildings based on TCN-LSTM-Attention[J].Control Theory & Applications,2025,42(11):2125~2135.[点击复制]
基于TCN-LSTM-Attention的建筑热动态与能耗预测
Thermal dynamics and energy consumption prediction of buildings based on TCN-LSTM-Attention
摘要点击 355  全文点击 64  投稿时间：2025-03-30  修订日期：2025-10-21
查看全文  查看/发表评论  下载PDF阅读器   HTML
DOI编号  10.7641/CTA.2025.50131
  2025,42(11):2125-2135
中文关键词  建筑状态预测  时间卷积网络  长短期记忆网络  注意力机制  粒子群优化算法
英文关键词  building condition prediction  temporal convolutional network  long short term memory  attention  particle swarm optimization algorithm
基金项目  国家自然科学基金项目(62192751,61425027)资助.
作者单位E-mail
付伟豪 清华大学自动化系和北京信息科学与技术国家研究中心 fwh22@mails.tsinghua.edu.cn 
赵千川* 清华大学自动化系和北京信息科学与技术国家研究中心 zhaoqc@tsinghua.edu.cn 
中文摘要
      基于暖通空调系统热动态与能耗的多变量耦合特点及数据预测精度不足的问题,本文提出一种融合时间 卷积–长短期记忆–注意力机制(TCN-LSTM-Attention)的融合预测模型. 首先,为了能够更加好捕获建筑运行数据 中的短期与长期依赖,建立了TCN-LSTM-Attention建筑热动态与能耗预测模型来预测HVAC能耗、室内温度、PMV; 采用改进粒子群算法(IPSO)优化预测模型超参数,降低模型预测误差,并对模型逼近能力进行分析;其次,使用En ergyPlus搭建建筑仿真模型并进行验证;以河北省某办公建筑运行数据进行预测模型仿真验证,实验表明本模型在 对比算法中有较好的预测精度和预测稳定性,并且验证了算法在建筑围护结构参数改变时的泛化性.
英文摘要
      Based on the multi-variable coupling characteristics of the thermal dynamics and energy consumption of the HVAC system and the problem of insufficient data prediction accuracy, this paper proposes a fusion prediction model integrating time convolution–long short–term memory–attention mechanism (TCN-LSTM-Attention). Firstly, in order to better capture the short-term and long-term dependencies in the building operation data, a TCN-LSTM-Attention building thermal dynamics and energy consumption prediction model is established to predict HVAC energy consumption, indoor temperature, and PMV. The improved particle swarm optimization (IPSO) algorithm is used to optimize the hyperparam eters of the prediction model, reduce the prediction error of the model, and analyze the model’s approximation ability. Secondly, the EnergyPlus is used to build a building simulation model for verification. The prediction model is verified by using the operation data of an office building in Hebei Province. The experiments show that this model has better prediction accuracy and prediction stability compared with the comparison algorithms, and the generalization of the algorithm when the building envelope parameters change is verified.