An improved transfer learning strategy for short-term cross-building energy prediction using data incremental

扫码查看

原文链接

万方数据

外文摘要：The available modelling data shortage issue makes it difficult to guarantee the performance of data-driven building energy prediction(BEP)models for both the newly built buildings and existing information-poor buildings.Both knowledge transfer learning(KTL)and data incremental learning(DIL)can address the data shortage issue of such buildings.For new building scenarios with continuous data accumulation,the performance of BEP models has not been fully investigated considering the data accumulation dynamics.DIL,which can learn dynamic features from accumulated data adapting to the developing trend of new building time-series data and extend BEP model's knowledge,has been rarely studied.Previous studies have shown that the performance of KTL models trained with fixed data can be further improved in scenarios with dynamically changing data.Hence,this study proposes an improved transfer learning cross-BEP strategy continuously updated using the coarse data incremental(CDI)manner.The hybrid KTL-DIL strategy(LSTM-DANN-CDI)uses domain adversarial neural network(DANN)for KLT and long short-term memory(LSTM)as the Baseline BEP model.Performance evaluation is conducted to systematically qualify the effectiveness and applicability of KTL and improved KTL-DIL.Real-world data from six-type 36 buildings of six types are adopted to evaluate the performance of KTL and KTL-DIL in data-driven BEP tasks considering factors like the model increment time interval,the available target and source building data volumes.Compared with LSTM,results indicate that KTL(LSTM-DANN)and the proposed KTL-DIL(LSTM-DANN-CDI)can significantly improve the BEP performance for new buildings with limited data.Compared with the pure KTL strategy LSTM-DANN,the improved KTL-DIL strategy LSTM-DANN-CDI has better prediction performance with an average performance improvement ratio of 60％.

外文关键词：

building energy prediction(BEP)cross-buildingdata incremental learning(DIL)domain adversarial neural network(DANN)knowledge transfer learning(KTL)

作者：

Guannan Li、Yubei Wu、Chengchu Yan、Xi Fang、Tao Li、Jiajia Gao、Chengliang Xu、Zixi Wang

展开 >

作者单位：

School of Urban Construction,Wuhan University of Science and Technology,Wuhan 430065,China

Anhui Province Key Laboratory of Intelligent Building and Building Energy-saving,Anhui Jianzhu University,Hefei 230601,China

State Key Laboratory of Green Building in Western China,Xi'an University of Architecture and Technology,Xi'an 710055,China

Key Laboratory of Low-grade Energy Utilization Technologies and Systems(Chongqing University),Ministry of Education of China,Chongqing University,Chongqing 400044,China

Hube

College of Urban Construction,Nanjing Tech University,No.200,North Zhongshan Road,Nanjing 210009,China

College of Civil Engineering,Hunan University,Changsha 410082,China

Hubei Provincial Engineering Research Center of Urban Regeneration,Wuhan University of Science and Technology,Wuhan 430065,China

展开 >

基金：

Opening Fund of Key Laboratory of Lowgrade Energy Utilization Technologies and Systems of Ministry of Education of China(ChoOpening Fund of State Key Laboratory of Green Building in Western Chinaopen Foundation of Anhui Province Key Laboratory of Intelligent Building and Building Energysaving"The 14th Five-Year Plan"Hubei Provincial advantaged characteristic disciplines(groups)project of Wuhan University of Science an"The 14th Five-Year Plan"Hubei Provincial advantaged characteristic disciplines(groups)project of Wuhan University of Science an国家自然科学基金2021 Construction Technology Plan Project of Hubei ProvinceScience and Technology Project of Guizhou Province

项目编号：

LLEUTS-202305LSKF202316IBES2022KF112023D05042023D0501519061812021-83Guizhou[2023]General 393

出版年：

2024

DOI：

10.1007/s12273-023-1053-x

建筑模拟(英文版)

ISSN：1996-3599

年,卷(期)：2024.17(1)

参考文献量64