Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network

Building energy consumption prediction (BECP) is the essential foundation for attaining energy efficiency in buildings, contributing significantly to tackling global energy challenges and facilitating energy sustainability. However, while data-driven methods have emerged as a crucial method to solvi...

Full description

Saved in:
Bibliographic Details
Main Authors: Bo Wang, Qiming Fu, You Lu, Ke Liu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/7/575
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406742987800576
author Bo Wang
Qiming Fu
You Lu
Ke Liu
author_facet Bo Wang
Qiming Fu
You Lu
Ke Liu
author_sort Bo Wang
collection DOAJ
description Building energy consumption prediction (BECP) is the essential foundation for attaining energy efficiency in buildings, contributing significantly to tackling global energy challenges and facilitating energy sustainability. However, while data-driven methods have emerged as a crucial method to solving this complex problem, the limited availability of data presents a significant challenge to model training. To address this challenge, this paper presents an innovative method, named Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network (LRTL-AtTCN). LRTL-AtTCN integrates the attention mechanism with temporal convolutional network (TCN), improving the ability of extracting global and local dependencies. Moreover, LRTL-AtTCN combines low-rank decomposition, reducing the number of parameters during the transfer learning process with similar buildings, which can achieve better transfer performance in the limited data case. Experimentally, we conduct a comprehensive evaluation across three forecasting horizons—1 week, 2 weeks, and 1 month. Compared to the horizon-matched baseline, LRTL-AtTCN cuts the MAE by 91.2%, 30.2%, and 26.4%, respectively, and lifts the 1-month R<sup>2</sup> from 0.8188 to 0.9286. On every horizon it also outperforms state-of-the-art transfer-learning methods, confirming its strong generalization and transfer capability in BECP.
format Article
id doaj-art-8dabb5256c3d44ad8ea8dfd4ff3fc0a8
institution Kabale University
issn 2078-2489
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-8dabb5256c3d44ad8ea8dfd4ff3fc0a82025-08-20T03:36:18ZengMDPI AGInformation2078-24892025-07-0116757510.3390/info16070575Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution NetworkBo Wang0Qiming Fu1You Lu2Ke Liu3School of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, ChinaSchool of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, ChinaSchool of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, ChinaJiangsu Province Engineering Research Center of Construction Carbon Neutral Technology, Suzhou University of Science and Technology, Suzhou 215009, ChinaBuilding energy consumption prediction (BECP) is the essential foundation for attaining energy efficiency in buildings, contributing significantly to tackling global energy challenges and facilitating energy sustainability. However, while data-driven methods have emerged as a crucial method to solving this complex problem, the limited availability of data presents a significant challenge to model training. To address this challenge, this paper presents an innovative method, named Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network (LRTL-AtTCN). LRTL-AtTCN integrates the attention mechanism with temporal convolutional network (TCN), improving the ability of extracting global and local dependencies. Moreover, LRTL-AtTCN combines low-rank decomposition, reducing the number of parameters during the transfer learning process with similar buildings, which can achieve better transfer performance in the limited data case. Experimentally, we conduct a comprehensive evaluation across three forecasting horizons—1 week, 2 weeks, and 1 month. Compared to the horizon-matched baseline, LRTL-AtTCN cuts the MAE by 91.2%, 30.2%, and 26.4%, respectively, and lifts the 1-month R<sup>2</sup> from 0.8188 to 0.9286. On every horizon it also outperforms state-of-the-art transfer-learning methods, confirming its strong generalization and transfer capability in BECP.https://www.mdpi.com/2078-2489/16/7/575building energy consumption predictiontransfer learninglow-rank decompositionTCN
spellingShingle Bo Wang
Qiming Fu
You Lu
Ke Liu
Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network
Information
building energy consumption prediction
transfer learning
low-rank decomposition
TCN
title Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network
title_full Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network
title_fullStr Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network
title_full_unstemmed Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network
title_short Limited Data Availability in Building Energy Consumption Prediction: A Low-Rank Transfer Learning with Attention-Enhanced Temporal Convolution Network
title_sort limited data availability in building energy consumption prediction a low rank transfer learning with attention enhanced temporal convolution network
topic building energy consumption prediction
transfer learning
low-rank decomposition
TCN
url https://www.mdpi.com/2078-2489/16/7/575
work_keys_str_mv AT bowang limiteddataavailabilityinbuildingenergyconsumptionpredictionalowranktransferlearningwithattentionenhancedtemporalconvolutionnetwork
AT qimingfu limiteddataavailabilityinbuildingenergyconsumptionpredictionalowranktransferlearningwithattentionenhancedtemporalconvolutionnetwork
AT youlu limiteddataavailabilityinbuildingenergyconsumptionpredictionalowranktransferlearningwithattentionenhancedtemporalconvolutionnetwork
AT keliu limiteddataavailabilityinbuildingenergyconsumptionpredictionalowranktransferlearningwithattentionenhancedtemporalconvolutionnetwork