Dynamically engineered multi-modal feature learning for predictions of office building cooling loads

Yiren LIU, Xiangyu ZHAO, S. Joe QIN*

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

2 Citations (Scopus)


This paper reports a new knowledge-driven engineered feature learning approach in response to the Global AI Challenge for Building E&M Facilities held by the Electrical and Mechanical Service Department (EMSD) of the Hong Kong SAR. The results were awarded with a Grand Prize by the competition organizer. A dynamically engineered multi-modal feature learning (DEMMFL) method is proposed for predicting the cooling load of two office buildings. The DEMMFL model is estimated with the Lasso-ridge regression and compared with other well-known methods such as the Lasso. The novel approach applies control system knowledge to engineer useful features and explore load patterns for multi-mode modeling. Deep learning methods including LSTM, GRU, and AutoGluon are implemented for automated machine learning and tested in parallel to compare the performance of the proposed model with existing methods. The proposed model is demonstrated to predict long-term cooling load most accurately using engineered features from weather information only.
Original languageEnglish
Article number122183
Number of pages15
JournalApplied Energy
Early online date15 Nov 2023
Publication statusPublished - 1 Feb 2024

Bibliographical note

The authors gratefully acknowledge the support of the EMSD E&M AI Lab of the Hong Kong SAR for providing the data. The authors acknowledge the assistance of Yixiao Huang, Shenglong Yao, and Guo Han on the LSTM, GRU, and AutoGluon work for comparison.

Publisher Copyright:
© 2023 The Author(s)


  • Feature engineering
  • Building energy management
  • Cooling load prediction
  • Sparse statistical learning
  • Automated machine learning


Dive into the research topics of 'Dynamically engineered multi-modal feature learning for predictions of office building cooling loads'. Together they form a unique fingerprint.

Cite this