Abstract

Automated detection of schedule- and operation-related energy savings opportunities in commercial buildings can help building owners lower operating expenses while also reducing adverse societal impacts such as global greenhouse gas emissions. We propose automated methods of identifying certain energy-efficiency opportunities (EEOs) in commercial buildings using only whole-building electricity consumption and local climate data. Our two-step approach uses piecewise linear regression and density-based robust regression model residual clustering to detect both schedule- and operation-related electricity consumption faults. This paper discusses results obtainedfrom applying this approach to two all-electric office buildings meant to demonstrate our model's effectiveness in identifying such EEOs. Ways by which the analysis results can be conveniently and succinctly presented to building managers and operators are also suggested.

LanguageEnglish (US)
Title of host publicationASHRAE Transactions - ASHRAE Winter Conference
PublisherAmer. Soc. Heating, Ref. Air-Conditoning Eng. Inc.
Pages422-433
Number of pages12
Volume122
ISBN (Electronic)9781939200259
StatePublished - 2016
Event2016 ASHRAE Winter Conference - Orlando, United States
Duration: Jan 23 2016Jan 27 2016

Other

Other2016 ASHRAE Winter Conference
CountryUnited States
CityOrlando
Period1/23/161/27/16

Fingerprint

Data mining
Energy efficiency
Electricity
Office buildings
Gas emissions
Greenhouse gases
Linear regression
Energy conservation
Managers

ASJC Scopus subject areas

  • Mechanical Engineering
  • Building and Construction

Cite this

Howard, P., Runger, G., Reddy, T. A., & Katipamula, S. (2016). Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data. In ASHRAE Transactions - ASHRAE Winter Conference (Vol. 122, pp. 422-433). Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc..

Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data. / Howard, Philip; Runger, George; Reddy, T. Agami; Katipamula, Srinivas.

ASHRAE Transactions - ASHRAE Winter Conference. Vol. 122 Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc., 2016. p. 422-433.

Research output: ResearchConference contribution

Howard, P, Runger, G, Reddy, TA & Katipamula, S 2016, Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data. in ASHRAE Transactions - ASHRAE Winter Conference. vol. 122, Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc., pp. 422-433, 2016 ASHRAE Winter Conference, Orlando, United States, 1/23/16.
Howard P, Runger G, Reddy TA, Katipamula S. Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data. In ASHRAE Transactions - ASHRAE Winter Conference. Vol. 122. Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc.2016. p. 422-433.
Howard, Philip ; Runger, George ; Reddy, T. Agami ; Katipamula, Srinivas. / Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data. ASHRAE Transactions - ASHRAE Winter Conference. Vol. 122 Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc., 2016. pp. 422-433
@inbook{65172f0f8436428daa5228b2bda52dbd,
title = "Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data",
abstract = "Automated detection of schedule- and operation-related energy savings opportunities in commercial buildings can help building owners lower operating expenses while also reducing adverse societal impacts such as global greenhouse gas emissions. We propose automated methods of identifying certain energy-efficiency opportunities (EEOs) in commercial buildings using only whole-building electricity consumption and local climate data. Our two-step approach uses piecewise linear regression and density-based robust regression model residual clustering to detect both schedule- and operation-related electricity consumption faults. This paper discusses results obtainedfrom applying this approach to two all-electric office buildings meant to demonstrate our model's effectiveness in identifying such EEOs. Ways by which the analysis results can be conveniently and succinctly presented to building managers and operators are also suggested.",
author = "Philip Howard and George Runger and Reddy, {T. Agami} and Srinivas Katipamula",
year = "2016",
volume = "122",
pages = "422--433",
booktitle = "ASHRAE Transactions - ASHRAE Winter Conference",
publisher = "Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc.",

}

TY - CHAP

T1 - Automated data mining methods for identifying energy efficiency opportunities using whole-building electricity data

AU - Howard,Philip

AU - Runger,George

AU - Reddy,T. Agami

AU - Katipamula,Srinivas

PY - 2016

Y1 - 2016

N2 - Automated detection of schedule- and operation-related energy savings opportunities in commercial buildings can help building owners lower operating expenses while also reducing adverse societal impacts such as global greenhouse gas emissions. We propose automated methods of identifying certain energy-efficiency opportunities (EEOs) in commercial buildings using only whole-building electricity consumption and local climate data. Our two-step approach uses piecewise linear regression and density-based robust regression model residual clustering to detect both schedule- and operation-related electricity consumption faults. This paper discusses results obtainedfrom applying this approach to two all-electric office buildings meant to demonstrate our model's effectiveness in identifying such EEOs. Ways by which the analysis results can be conveniently and succinctly presented to building managers and operators are also suggested.

AB - Automated detection of schedule- and operation-related energy savings opportunities in commercial buildings can help building owners lower operating expenses while also reducing adverse societal impacts such as global greenhouse gas emissions. We propose automated methods of identifying certain energy-efficiency opportunities (EEOs) in commercial buildings using only whole-building electricity consumption and local climate data. Our two-step approach uses piecewise linear regression and density-based robust regression model residual clustering to detect both schedule- and operation-related electricity consumption faults. This paper discusses results obtainedfrom applying this approach to two all-electric office buildings meant to demonstrate our model's effectiveness in identifying such EEOs. Ways by which the analysis results can be conveniently and succinctly presented to building managers and operators are also suggested.

UR - http://www.scopus.com/inward/record.url?scp=84974855942&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84974855942&partnerID=8YFLogxK

M3 - Conference contribution

VL - 122

SP - 422

EP - 433

BT - ASHRAE Transactions - ASHRAE Winter Conference

PB - Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc.

ER -