Physical and JIT model-based hybrid modeling approach for building thermal load prediction

Yutaka Iino, Masahiko Murai, Dai Murayama, Ichiro Motoyama

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Energy conservation in building fields is a key issue from an environmental point of view as well as of the industrial, transportation, and residential fields. Half of the total energy consumption in a building is a result of HVAC (heating, ventilation, and air conditioning) systems. In order to conserve energy in an HVAC system, a thermal load prediction model for a building is required. This paper proposes a hybrid modeling approach using a physical and just-in-time (JIT) model for the thermal load predictions for a building. The proposed method has features and benefits such as (1) it is applicable to cases in which past operating data for load prediction model learning are poor; (2) it has a self-checking function, which determines if the data-driven load prediction and the physical-based one are consistent at all times, so that it can determine if something is wrong in the load prediction procedure; (3) it has the ability to adjust the load prediction in real time against a sudden change in the model parameters and environmental conditions. The proposed method is evaluated using real operating data from an existing building, and the improvement in load prediction performance is illustrated.

Original languageEnglish
Pages (from-to)30-39
Number of pages10
JournalElectrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)
Volume185
Issue number2
DOIs
Publication statusPublished - 2013 Nov 1

Keywords

  • building and energy management system (BEMS)
  • just-in-time (JIT) modeling
  • physical model
  • thermal load prediction

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Physical and JIT model-based hybrid modeling approach for building thermal load prediction'. Together they form a unique fingerprint.

  • Cite this