skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Online Learning for Commercial Buildings

Abstract

There has been an increased interest in designing optimization based techniques for the control of building heating, ventilation, and air-conditioning (HVAC) systems for either improving the energy efficiency of buildings or providing ancillary services to the electric grid. The performance of such prediction-based control techniques heavily rely on the model of a building’s thermal dynamics. However, the development of high fidelity building thermal dynamic models is challenging given the presence of large uncertainties that affect thermal loads in buildings such as building envelope performance, thermal mass, internal heat gains as well as occupants' behavior. In this paper, we propose a method to identify both a resistive-capacitive parametric model, and non -parametric load uncertainties using measured input-output data. The parametric model is obtained using semi-parametric regression, whereas the non-parametric part is based on Random Forest, where regression trees are used to derive the dependency of non-parametric terms on both building operation parameters and ambient temperature. The effectiveness of the method is evaluated using experimental data collected from an office building at the Pacific Northwest National Laboratory (PNNL) campus. The proposed methodology was observed to provide improved accuracy over appropriate baseline strategies, when predicting indoor air temperatures.

Authors:
 [1];  [2];  [1];  [2];  [2];  [2];  [3]
  1. Oak Ridge National Laboratory
  2. BATTELLE (PACIFIC NW LAB)
  3. OAK RIDGE NATIONAL LAB
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1582641
Report Number(s):
PNNL-SA-138212
DOE Contract Number:  
AC05-76RL01830
Resource Type:
Conference
Resource Relation:
Conference: Proceedings of the Tenth ACM International Conference on Future Energy Systems (e-Energy 2019), June 25-28, 2019, Phoenix, AZ
Country of Publication:
United States
Language:
English

Citation Formats

Dong, Jin, Ramachandran, Thiagarajan, Im, Piljae, Huang, Sen, Chandan, Vikas, Vrabie, Draguna L., and Kuruganti, Phani Teja V. Online Learning for Commercial Buildings. United States: N. p., 2019. Web. doi:10.1145/3307772.3331029.
Dong, Jin, Ramachandran, Thiagarajan, Im, Piljae, Huang, Sen, Chandan, Vikas, Vrabie, Draguna L., & Kuruganti, Phani Teja V. Online Learning for Commercial Buildings. United States. doi:10.1145/3307772.3331029.
Dong, Jin, Ramachandran, Thiagarajan, Im, Piljae, Huang, Sen, Chandan, Vikas, Vrabie, Draguna L., and Kuruganti, Phani Teja V. Fri . "Online Learning for Commercial Buildings". United States. doi:10.1145/3307772.3331029.
@article{osti_1582641,
title = {Online Learning for Commercial Buildings},
author = {Dong, Jin and Ramachandran, Thiagarajan and Im, Piljae and Huang, Sen and Chandan, Vikas and Vrabie, Draguna L. and Kuruganti, Phani Teja V.},
abstractNote = {There has been an increased interest in designing optimization based techniques for the control of building heating, ventilation, and air-conditioning (HVAC) systems for either improving the energy efficiency of buildings or providing ancillary services to the electric grid. The performance of such prediction-based control techniques heavily rely on the model of a building’s thermal dynamics. However, the development of high fidelity building thermal dynamic models is challenging given the presence of large uncertainties that affect thermal loads in buildings such as building envelope performance, thermal mass, internal heat gains as well as occupants' behavior. In this paper, we propose a method to identify both a resistive-capacitive parametric model, and non -parametric load uncertainties using measured input-output data. The parametric model is obtained using semi-parametric regression, whereas the non-parametric part is based on Random Forest, where regression trees are used to derive the dependency of non-parametric terms on both building operation parameters and ambient temperature. The effectiveness of the method is evaluated using experimental data collected from an office building at the Pacific Northwest National Laboratory (PNNL) campus. The proposed methodology was observed to provide improved accuracy over appropriate baseline strategies, when predicting indoor air temperatures.},
doi = {10.1145/3307772.3331029},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2019},
month = {6}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: