MITP-Net: A deep-learning framework for short-term indoor temperature predictions in multi-zone buildings

Indoor temperature prediction is an essential component of building control and energy saving. Although existing indoor temperature prediction frameworks have achieved remarkable progress, they struggle to achieve high performance due to information, method, application, and sim-to-real gaps. Aiming...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Building and environment Ročník 239; s. 110388
Hlavní autoři:	Xing, Tian, Sun, Kailai, Zhao, Qianchuan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.07.2023
Témata:	Encoder–decoder architecture Gated recurrent unit network Information fusion Multi-zone temperature prediction Multiple sensor information Encoder–decoder architecture Multi-zone temperature prediction Multiple sensor information Gated recurrent unit network Information fusion
ISSN:	0360-1323, 1873-684X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Indoor temperature prediction is an essential component of building control and energy saving. Although existing indoor temperature prediction frameworks have achieved remarkable progress, they struggle to achieve high performance due to information, method, application, and sim-to-real gaps. Aiming to fill these gaps, we propose a novel deep-learning framework for short-term indoor temperature prediction in multi-zone buildings. In particular, we expand the sensing information and formulate the multi-zone indoor temperature prediction (MITP) problem. To improve the prediction performance, we employ information fusion and encoder–decoder architecture to the MITP problem and propose MITP-Net. We set up 11 ablation experiments to compare the prediction performance of relative frameworks. To evaluate frameworks’ performance, we publicly release a dataset including 2-week real operating data in a multi-zone office with a 1-min sampling interval (829,440 digits in total). Compared with existing deep-learning frameworks, MITP-Net significantly raises the prediction accuracy and can flexibly adjust the lengths of input and prediction sequences for different requirements. We provide the usage steps of MITP-Net and publish the operating data and codes on the GitHub repository: https://github.com/XingTian1994/MITP-Net. •We formulate the MITP problem and propose a novel deep-learning prediction framework.•MITP-Net utilizes a two-stage information fusion method for multi-modal data.•MITP-Net adopts the encoder–decoder architecture for variable sequences length.•We publicly release a real multi-zone office dataset and verify MITP-Net.•MITP-Net significantly improves the performance compared to existing methods.
ISSN:	0360-1323 1873-684X
DOI:	10.1016/j.buildenv.2023.110388