Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Performance analysis and comparison of data-driven models for predicting indoor temperature in multi-zone commercial buildings

Journal Article · · Energy and Buildings
 [1];  [1];  [1];  [1]
  1. Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
+ Show Author Affiliations
Building thermal models, which characterize the properties of a building’s envelope and thermal mass, are essential for accurate indoor temperature and cooling/heating demand prediction. Because of their flexibility and ease of use, data-driven models are increasingly used. Here, this study compared and analyzed the performance of gray-box (resistance-capacitance) and black-box (recurrent neural network) models for predicting indoor air temperature in a real multi-zone commercial building. The developed resistance-capacitance model served as a benchmark model for which full sets of temporal data and building information were used as inputs. The recurrent neural network models were trained and tested assuming various available types and amounts of temporal data and known building physical information to investigate the effects of data and information availability. Feature importance analysis was conducted to select the key variables for different prediction targets under different scenarios. This research provides guidance in selecting an appropriate building thermal response modeling method based on the measured data availability, building physical information, and application.
Research Organization:
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
Sponsoring Organization:
USDOE; USDOE Office of Energy Efficiency and Renewable Energy (EERE), Office of Sustainable Transportation. Bioenergy Technologies Office (BETO); USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF)
Grant/Contract Number:
AC05-00OR22725
OSTI ID:
2000358
Alternate ID(s):
OSTI ID: 1999302
Journal Information:
Energy and Buildings, Journal Name: Energy and Buildings Journal Issue: 1 Vol. 298; ISSN 0378-7788
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (47)

Community-scale residential air conditioning control for effective grid management journal October 2014
A fast chiller power demand response control strategy for buildings connected to smart grid journal January 2015
Design optimization and optimal control of grid-connected and standalone nearly/net zero energy buildings journal October 2015
Model-based optimal design of active cool thermal energy storage for maximal life-cycle cost saving from demand management in commercial buildings journal September 2017
A short-term building cooling load prediction method using deep learning algorithms journal June 2017
Constructing large scale surrogate models from big data and artificial intelligence journal September 2017
Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks journal February 2018
Predicting heating demand and sizing a stratified thermal storage tank using deep learning algorithms journal October 2018
Real-time prediction model for indoor temperature in a commercial building journal December 2018
A hybrid building thermal modeling approach for predicting temperatures in typical, detached, two-story houses journal February 2019
Assessment of deep recurrent neural network-based strategies for short-term building energy predictions journal February 2019
Frequency control of air conditioners in response to real-time dynamic electricity prices in smart grids journal May 2019
Empirical validation of building energy modeling for multi-zones commercial buildings in cooling season journal March 2020
Building thermal load prediction through shallow machine learning and deep learning journal April 2020
Model predictive control with adaptive machine-learning-based model for building energy efficiency and comfort optimization journal August 2020
Space cooling energy usage prediction based on utility data for residential buildings using machine learning methods journal June 2021
A machine learning-based framework for cost-optimal building retrofit journal July 2021
Attention-based interpretable neural network for building cooling load prediction journal October 2021
Physics informed neural networks for control oriented thermal modeling of buildings journal May 2022
A state-space modeling approach and multi-level optimization algorithm for predictive control of multi-zone buildings with mixed-mode cooling journal October 2014
Ten questions concerning model predictive control for energy efficient buildings journal August 2016
Comparative analysis on predictability of natural ventilation rate based on machine learning algorithms journal May 2021
The use of machine learning to determine moisture recovery in a heat wheel and its impact on indoor moisture journal May 2022
A method for model-reduction of non-linear thermal dynamics of multi-zone buildings journal April 2012
Reduced-order residential home modeling for model predictive control journal May 2014
HVAC system design under peak load prediction uncertainty using multiple-criterion decision making technique journal March 2015
Physical parameters identification of walls using ARX models obtained by deduction journal December 2015
A hybrid model approach for forecasting future residential electricity consumption journal April 2016
A modeling framework for optimal energy management of a residential building journal October 2016
Development of RC model for thermal dynamic analysis of buildings through model structure simplification journal July 2019
Data-driven modeling of building thermal dynamics: Methodology and state of the art journal November 2019
Identifying grey-box thermal models with Bayesian neural networks journal May 2021
Physics-constrained deep learning of multi-zone building thermal dynamics journal July 2021
Analysis of feature matrix in machine learning algorithms to predict energy consumption of public buildings journal October 2021
Application of machine learning to estimate building energy use intensities journal October 2021
A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control journal May 2018
Load shifting potential assessment of building thermal storage performance for building design journal March 2022
Model-based predictive control of multi-zone commercial building with a lumped building modelling approach journal January 2023
Load demand forecasting of residential buildings using a deep learning model journal February 2020
Performance evaluation of a dynamic wall integrated with active insulation and thermal energy storage systems journal February 2022
Simplified building model for transient thermal performance estimation using GA-based parameter identification journal April 2006
A simplified dynamic model for existing buildings using CTF and thermal network models journal September 2008
Modeling techniques used in building HVAC control systems: A review journal March 2018
Grey-box modeling and application for building energy simulations - A critical review journal August 2021
A data-driven interval forecasting model for building energy prediction using attention-based LSTM and fuzzy information granulation journal January 2022
Identification of multi-zone grey-box building models for use in model predictive control journal May 2020
Improving Accuracy and Generalization Performance of Small-Size Recurrent Neural Networks Applied to Short-Term Load Forecasting journal December 2020

Figures / Tables (23)

Table 1(p. 7)table Table 1
Fig. 1(p. 8)figure Fig. 1
Fig.2(p. 9)figure Fig.2
Fig. 3(p. 12)figure Fig. 3
Fig. 4(p. 13)figure Fig. 4
Fig. 5(p. 14)figure Fig. 5
Table 2(p. 15)table Table 2
Table 3(p. 16)table Table 3
Table 4(p. 17)table Table 4
Fig. 6(p. 19)figure Fig. 6
Fig. 7(p. 20)figure Fig. 7
Fig. 8(p. 21)figure Fig. 8
Fig. 9(p. 22)figure Fig. 9
Fig. 10: Part 1(p. 23)figure Fig. 10: Part 1
Fig. 10: Part 2(p. 24)figure Fig. 10: Part 2
Fig. 11: Part 1(p. 25)figure Fig. 11: Part 1
Fig. 11: Part 2(p. 26)figure Fig. 11: Part 2
Fig. 12: Part 1(p. 27)figure Fig. 12: Part 1
Fig. 12: Part 2(p. 28)figure Fig. 12: Part 2
Fig. 13: Part 2(p. 30)figure Fig. 13: Part 2
Fig. 14: Part 1(p. 30)figure Fig. 14: Part 1
Fig. 14: Part 2(p. 31)figure Fig. 14: Part 2
Fig. 14: Part 3(p. 32)figure Fig. 14: Part 3

Similar Records

Grey-box and ANN-based building models for multistep-ahead prediction of indoor temperature to implement model predictive control
Journal Article · Sun Sep 10 20:00:00 EDT 2023 · Engineering Applications of Artificial Intelligence · OSTI ID:2229217
Physics vs. Structure: A Systematic Benchmark of Learning Strategies for Multi-Zone Building Thermal Dynamics
Journal Article · Sun Jun 14 20:00:00 EDT 2026 · Energy and Buildings · OSTI ID:3029725
Online Learning for Commercial Buildings
Conference · Sat Jun 01 00:00:00 EDT 2019 · OSTI ID:1530112

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Building envelope thermal model
Feature importance analysis
Machine learning
Recurrent neural network
Resistance-capacitance model
Time series data