EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Heterogeneous Deep Integration Model Framework for Typical VAV–Reheat Air Conditioning Systems

Jun Zhu, Shengze Lu, Xin Yang, Xue Zhou, Yuexia Sun, Shoujie Song, Jiying Liu

Buildings · 13.07.2026 · 16 (14) · 2778

DOI: 10.3390/buildings16142778 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Buildings, online erschienen am 13.07.2026. Verfasst von Jun Zhu und 6 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Addressing the deficiencies of data-driven heating, ventilation, and air conditioning (HVAC) models in multi-objective joint prediction, long-horizon prediction accuracy, and uncertainty quantification, this study proposes a heterogeneous deep ensemble framework. Through co-simulation technology, a multi-operating-condition operational dataset for a typical variable air volume (VAV)–Reheat system was constructed. By adopting an operating-condition-level partitioning strategy, the input features were strictly decoupled into historical system states, internal loads, and external control commands. On this basis, the framework integrates the advantages of Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU), and Temporal Convolutional Networks (TCN). Utilizing an inverse-variance weighting mechanism, it achieves the synchronous and accurate prediction of 11-dimensional targets, encompassing total system power, five-zone temperatures, and five-zone CO2 concentrations. Simultaneously, the prediction divergence among the ensemble models is utilized to quantify epistemic uncertainty, and a variance scanning mechanism is introduced to calibrate the prediction confidence intervals. The results indicate that within a 6 h prediction horizon, the absolute errors of the model in power, temperature, and CO2 are reduced by 80.17%, 63–72%, and 75–80.62%, respectively, compared to the physical baseline. On the independent test set, the actual coverage rate of the calibrated prediction intervals approaches 90%, exhibiting an adaptive enveloping variation characterized by tightening during steady states and widening during transients. The proposed heterogeneous ensemble framework demonstrates superior prediction accuracy and long-horizon prediction stability, providing reliable model support for multi-objective optimal operation and robust control of buildings.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Zhu, J., Lu, S., Yang, X., Zhou, X., Sun, Y., Song, S., & Liu, J. (2026). Heterogeneous Deep Integration Model Framework for Typical VAV–Reheat Air Conditioning Systems. Buildings, 16(14), 2778. https://doi.org/10.3390/buildings16142778

Vancouver

Zhu J, Lu S, Yang X, Zhou X, Sun Y, Song S, et al. Heterogeneous Deep Integration Model Framework for Typical VAV–Reheat Air Conditioning Systems. Buildings. 2026;16(14):2778. doi:10.3390/buildings16142778

BibTeX
@article{Zhu2026,
  author = {Zhu, Jun and Lu, Shengze and Yang, Xin and Zhou, Xue and Sun, Yuexia and Song, Shoujie and Liu, Jiying},
  title = {Heterogeneous Deep Integration Model Framework for Typical VAV–Reheat Air Conditioning Systems},
  journal = {Buildings},
  year = {2026},
  volume = {16},
  number = {14},
  pages = {2778},
  doi = {10.3390/buildings16142778}
}
Kostenlos starten →