Data-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information
Abstract
Understanding the models that characterize the thermal dynamics in a smart building is important for the comfort of its occupants and for its energy optimization. Here, a significant amount of research has attempted to utilize thermodynamics (physical) models for smart building control, but these approaches remain challenging due to the stochastic nature of the intermittent environmental disturbances. This paper presents a novel data-driven approach for indoor thermal model inference, which combines an Autoregressive Moving Average with eXogenous inputs model (ARMAX) with a Normalized Mutual Information scheme (NMI). Based on this information-theoretic method, NMI, causal dependencies between the indoor temperature and exogenous inputs are explicitly obtained as a guideline for the ARMAX model to find the dominating inputs. For validation, we use three datasets based on building energy systems-against which we compare our method to an autoregressive model with exogenous inputs (ARX), a regularized ARMAX model, and state-space models.
- Authors:
-
[2];
- Iowa State Univ., Ames, IA (United States)
- Bosch Research & Technology Center North America, Pittsburgh, PA (United States)
- Carnegie Mellon Univ., Pittsburgh, PA (United States)
- Publication Date:
- Research Org.:
- Carnegie Mellon Univ., Pittsburgh, PA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office; National Science Foundation (NSF)
- OSTI Identifier:
- 1812201
- Report Number(s):
- DOE-CMU-07682
Journal ID: ISSN 2378-5861
- Grant/Contract Number:
- EE0007682; EPSC-1101284
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Proceedings of the American Control Conference (ACC) (Online)
- Additional Journal Information:
- Journal Name: Proceedings of the American Control Conference (ACC) (Online); Journal Volume: 2018; Conference: 2018 Annual American Control Conference (ACC), Milwaukee, WI (United States), 27-29 Jun 2018; Journal ID: ISSN 2378-5861
- Publisher:
- IEEE
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; Thermal dynamics; Disturbances; Smart buildings; Sensing; Mutual information; ARMAX; Autoregressive; State space
Citation Formats
Jiang, Zhanhong, Francis, Jonathan, Sahu, Anit Kumar, Munir, Sirajum, Shelton, Charles, Rowe, Anthony, and Berges, Mario. Data-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information. United States: N. p., 2018.
Web. doi:10.23919/acc.2018.8431085.
Jiang, Zhanhong, Francis, Jonathan, Sahu, Anit Kumar, Munir, Sirajum, Shelton, Charles, Rowe, Anthony, & Berges, Mario. Data-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information. United States. https://doi.org/10.23919/acc.2018.8431085
Jiang, Zhanhong, Francis, Jonathan, Sahu, Anit Kumar, Munir, Sirajum, Shelton, Charles, Rowe, Anthony, and Berges, Mario. Fri .
"Data-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information". United States. https://doi.org/10.23919/acc.2018.8431085. https://www.osti.gov/servlets/purl/1812201.
@article{osti_1812201,
title = {Data-driven Thermal Model Inference with ARMAX, in Smart Environments, based on Normalized Mutual Information},
author = {Jiang, Zhanhong and Francis, Jonathan and Sahu, Anit Kumar and Munir, Sirajum and Shelton, Charles and Rowe, Anthony and Berges, Mario},
abstractNote = {Understanding the models that characterize the thermal dynamics in a smart building is important for the comfort of its occupants and for its energy optimization. Here, a significant amount of research has attempted to utilize thermodynamics (physical) models for smart building control, but these approaches remain challenging due to the stochastic nature of the intermittent environmental disturbances. This paper presents a novel data-driven approach for indoor thermal model inference, which combines an Autoregressive Moving Average with eXogenous inputs model (ARMAX) with a Normalized Mutual Information scheme (NMI). Based on this information-theoretic method, NMI, causal dependencies between the indoor temperature and exogenous inputs are explicitly obtained as a guideline for the ARMAX model to find the dominating inputs. For validation, we use three datasets based on building energy systems-against which we compare our method to an autoregressive model with exogenous inputs (ARX), a regularized ARMAX model, and state-space models.},
doi = {10.23919/acc.2018.8431085},
journal = {Proceedings of the American Control Conference (ACC) (Online)},
number = ,
volume = 2018,
place = {United States},
year = {Fri Jun 01 00:00:00 EDT 2018},
month = {Fri Jun 01 00:00:00 EDT 2018}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
A comparison of linear and neural network ARX models applied to a prediction of the indoor temperature of a building
journal, April 2004
- Zouak, M.; Mechaqrane, A.
- Neural Computing & Applications, Vol. 13, Issue 1
A physics-based linear parametric model of room temperature in office buildings
journal, April 2012
- Wu, Siyu; Sun, Jian-Qiao
- Building and Environment, Vol. 50
A comparison of linear and neural network ARX models applied to a prediction of the indoor temperature of a building
journal, April 2004
- Zouak, M.; Mechaqrane, A.
- Neural Computing & Applications, Vol. 13, Issue 1
Accurate occupancy detection of an office room from light, temperature, humidity and CO 2 measurements using statistical learning models
journal, January 2016
- Candanedo, Luis M.; Feldheim, Véronique
- Energy and Buildings, Vol. 112
Information-Theoretic Measures for Knowledge Discovery and Data Mining
book, January 2003
- Yao, Y. Y.
- Entropy Measures, Maximum Entropy Principle and Emerging Applications
Entropy and Correlation: Some Comments
journal, January 1987
- Kvalseth, Tarald O.
- IEEE Transactions on Systems, Man, and Cybernetics, Vol. 17, Issue 3
On-line learning of indoor temperature forecasting models towards energy efficiency
journal, November 2014
- Zamora-Martínez, F.; Romeu, P.; Botella-Rocamora, P.
- Energy and Buildings, Vol. 83
Comparative Evaluation of Control-Oriented Zone Temperature Prediction Modeling Strategies in Buildings
conference, October 2015
- Chinde, Venkatesh; Heylmun, Jeffrey C.; Kohl, Adam
- Volume 2: Diagnostics and Detection; Drilling; Dynamics and Control of Wind Energy Systems; Energy Harvesting; Estimation and Identification; Flexible and Smart Structure Control; Fuels Cells/Energy Storage; Human Robot Interaction; HVAC Building Energy Management; Industrial Applications; Intelligent Transportation Systems; Manufacturing; Mechatronics; Modelling and Validation; Motion and Vibration Control Applications
Modelling temperature in intelligent buildings by means of autoregressive models
journal, August 2007
- Ríos-Moreno, G. J.; Trejo-Perea, M.; Castañeda-Miranda, R.
- Automation in Construction, Vol. 16, Issue 5
Coupling a neural network temperature predictor and a fuzzy logic controller to perform thermal comfort regulation in an office building
journal, February 2014
- Marvuglia, Antonino; Messineo, Antonio; Nicolosi, Giuseppina
- Building and Environment, Vol. 72
ANN-based thermal control models for residential buildings
journal, July 2010
- Moon, Jin Woo; Kim, Jong-Jin
- Building and Environment, Vol. 45, Issue 7
Algorithm for optimal application of the setback moment in the heating season using an artificial neural network model
journal, September 2016
- Moon, Jin Woo; Jung, Sung Kwon
- Energy and Buildings, Vol. 127
Applications of artificial neural-networks for energy systems
journal, September 2000
- Kalogirou, Soteris A.
- Applied Energy, Vol. 67, Issue 1-2
A review of thermal comfort models and indicators for indoor environments
journal, November 2017
- Enescu, Diana
- Renewable and Sustainable Energy Reviews, Vol. 79
Development of room temperature and relative humidity linear parametric models for an open office using BMS data
journal, March 2010
- Mustafaraj, G.; Chen, J.; Lowry, G.
- Energy and Buildings, Vol. 42, Issue 3