Data mining of space heating system performance in affordable housing
Abstract
The space heating in residential buildings accounts for a considerable amount of the primary energy use. Therefore, understanding the operation and performance of space heating systems becomes crucial in improving occupant comfort while reducing energy use. This study investigated the behavior of occupants adjusting their thermostat settings and heating system operations in a 62-unit affordable housing complex in Revere, Massachusetts, USA. The data mining methods, including clustering approach and decision trees, were used to ascertain occupant behavior patterns. Data tabulating ON/OFF space heating states was assessed, to provide a better understanding of the intermittent operation of space heating systems in terms of system cycling frequency and the duration of each operation. The decision tree was used to verify the link between room temperature settings, house and heating system characteristics and the heating energy use. The results suggest that the majority of apartments show fairly constant room temperature profiles with limited variations during a day or between weekday and weekend. Data clustering results revealed six typical patterns of room temperature profiles during the heating season. Space heating systems cycled more frequently than anticipated due to a tight range of room thermostat settings and potentially oversized heating capacities. In conclusion, from thismore »
- Authors:
-
- Tsinghua Univ., Beijing (China)
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1253721
- Alternate Identifier(s):
- OSTI ID: 1247779
- Report Number(s):
- LBNL-180239
Journal ID: ISSN 0360-1323; ir:180239
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Building and Environment
- Additional Journal Information:
- Journal Volume: 89; Journal Issue: C; Journal ID: ISSN 0360-1323
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; data mining; space heating; affordable housing; occupant behavior; building simulation; clustering; decision tree
Citation Formats
Ren, Xiaoxin, Yan, Da, and Hong, Tianzhen. Data mining of space heating system performance in affordable housing. United States: N. p., 2015.
Web. doi:10.1016/j.buildenv.2015.02.009.
Ren, Xiaoxin, Yan, Da, & Hong, Tianzhen. Data mining of space heating system performance in affordable housing. United States. https://doi.org/10.1016/j.buildenv.2015.02.009
Ren, Xiaoxin, Yan, Da, and Hong, Tianzhen. Mon .
"Data mining of space heating system performance in affordable housing". United States. https://doi.org/10.1016/j.buildenv.2015.02.009. https://www.osti.gov/servlets/purl/1253721.
@article{osti_1253721,
title = {Data mining of space heating system performance in affordable housing},
author = {Ren, Xiaoxin and Yan, Da and Hong, Tianzhen},
abstractNote = {The space heating in residential buildings accounts for a considerable amount of the primary energy use. Therefore, understanding the operation and performance of space heating systems becomes crucial in improving occupant comfort while reducing energy use. This study investigated the behavior of occupants adjusting their thermostat settings and heating system operations in a 62-unit affordable housing complex in Revere, Massachusetts, USA. The data mining methods, including clustering approach and decision trees, were used to ascertain occupant behavior patterns. Data tabulating ON/OFF space heating states was assessed, to provide a better understanding of the intermittent operation of space heating systems in terms of system cycling frequency and the duration of each operation. The decision tree was used to verify the link between room temperature settings, house and heating system characteristics and the heating energy use. The results suggest that the majority of apartments show fairly constant room temperature profiles with limited variations during a day or between weekday and weekend. Data clustering results revealed six typical patterns of room temperature profiles during the heating season. Space heating systems cycled more frequently than anticipated due to a tight range of room thermostat settings and potentially oversized heating capacities. In conclusion, from this study affirm data mining techniques are an effective method to analyze large datasets and extract hidden patterns to inform design and improve operations.},
doi = {10.1016/j.buildenv.2015.02.009},
journal = {Building and Environment},
number = C,
volume = 89,
place = {United States},
year = {Mon Feb 16 00:00:00 EST 2015},
month = {Mon Feb 16 00:00:00 EST 2015}
}
Web of Science
Works referenced in this record:
A review on buildings energy consumption information
journal, January 2008
- Pérez-Lombard, Luis; Ortiz, José; Pout, Christine
- Energy and Buildings, Vol. 40, Issue 3
Linking Life-Styles and Energy Use: A Matter of Time?
journal, November 1989
- Schipper, L.; Bartlett, S.; Hawk, D.
- Annual Review of Energy, Vol. 14, Issue 1
A novel approach for building occupancy simulation
journal, June 2011
- Wang, Chuang; Yan, Da; Jiang, Yi
- Building Simulation, Vol. 4, Issue 2
Quantitative description and simulation of human behavior in residential buildings
journal, November 2011
- Peng, Chen; Yan, Da; Wu, Ruhong
- Building Simulation, Vol. 5, Issue 2
Air-conditioning usage conditional probability model for residential buildings
journal, November 2014
- Ren, Xiaoxin; Yan, Da; Wang, Chuang
- Building and Environment, Vol. 81
A unified model for the simulation of oil, gas and biomass space heating boilers for energy estimating purposes. Part I: Model development
journal, March 2011
- Haller†, M. Y.; Paavilainen, J.; Konersmann, L.
- Journal of Building Performance Simulation, Vol. 4, Issue 1
A microsimulation model of urban energy use: Modelling residential space heating demand in ILUTE
journal, March 2012
- Chingcuanco, Franco; Miller, Eric J.
- Computers, Environment and Urban Systems, Vol. 36, Issue 2
Interaction between building design, management, household and individual factors in relation to energy use for space heating in apartment buildings
journal, October 2014
- Engvall, Karin; Lampa, Erik; Levin, Per
- Energy and Buildings, Vol. 81
How people use thermostats in homes: A review
journal, December 2011
- Peffer, Therese; Pritoni, Marco; Meier, Alan
- Building and Environment, Vol. 46, Issue 12
Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis
journal, March 2014
- Du, Zhimin; Fan, Bo; Jin, Xinqiao
- Building and Environment, Vol. 73
Data mining in building automation system for improving building operational performance
journal, June 2014
- Xiao, Fu; Fan, Cheng
- Energy and Buildings, Vol. 75
Minimizing energy consumption of an air handling unit with a computational intelligence approach
journal, May 2013
- Kusiak, Andrew; Zeng, Yaohui; Xu, Guanglin
- Energy and Buildings, Vol. 60
A decision support model for improving a multi-family housing complex based on CO2 emission from gas energy consumption
journal, June 2012
- Hong, Taehoon; Koo, Choongwan; Park, Sungki
- Building and Environment, Vol. 52
Modeling and short-term prediction of HVAC system with a clustering algorithm
journal, October 2014
- Tang, Fan; Kusiak, Andrew; Wei, Xiupeng
- Energy and Buildings, Vol. 82
A systematic procedure to study the influence of occupant behavior on building energy consumption
journal, June 2011
- Yu, Zhun; Fung, Benjamin C. M.; Haghighat, Fariborz
- Energy and Buildings, Vol. 43, Issue 6
A novel methodology for knowledge discovery through mining associations between building operational data
journal, April 2012
- Yu, Zhun (Jerry); Haghighat, Fariborz; Fung, Benjamin C. M.
- Energy and Buildings, Vol. 47
Recognition of emergent human behaviour in a smart home: A data mining approach
journal, March 2007
- Lühr, Sebastian; West, Geoff; Venkatesh, Svetha
- Pervasive and Mobile Computing, Vol. 3, Issue 2
Understanding the indoor environment through mining sensory data—A case study
journal, November 2007
- Wu, Shaomin; Clements-Croome, Derek
- Energy and Buildings, Vol. 39, Issue 11
Data association mining for identifying lighting energy waste patterns in educational institutes
journal, July 2013
- Motta Cabrera, David F.; Zareipour, Hamidreza
- Energy and Buildings, Vol. 62
A data-mining approach to discover patterns of window opening and closing behavior in offices
journal, December 2014
- D'Oca, Simona; Hong, Tianzhen
- Building and Environment, Vol. 82
Occupancy schedules learning process through a data mining framework
journal, February 2015
- D’Oca, Simona; Hong, Tianzhen
- Energy and Buildings, Vol. 88
Occupant behavior and schedule modeling for building energy simulation through office appliance power consumption data mining
journal, October 2014
- Zhao, Jie; Lasternas, Bertrand; Lam, Khee Poh
- Energy and Buildings, Vol. 82
Simplifying decision trees
journal, September 1987
- Quinlan, J. R.
- International Journal of Man-Machine Studies, Vol. 27, Issue 3
Validity index for clusters of different sizes and densities
journal, January 2011
- Žalik, Krista Rizman; Žalik, Borut
- Pattern Recognition Letters, Vol. 32, Issue 2
Works referencing / citing this record:
A regression data mining approach in Lean Production
journal, March 2018
- Bragança, Ricardo; Portela, Filipe; Santos, Manuel
- Concurrency and Computation: Practice and Experience, Vol. 31, Issue 22
Modeling occupancy and behavior for better building design and operation—A critical review
journal, June 2018
- Dong, Bing; Yan, Da; Li, Zhaoxuan
- Building Simulation, Vol. 11, Issue 5
Triggering Optimal Control of Air Conditioning Systems by Event-Driven Mechanism: Comparing Direct and Indirect Approaches
journal, October 2019
- Wang, Junqi; Liu, Rundong; Zhang, Linfeng
- Energies, Vol. 12, Issue 20