A new clustering method to identify outliers and diurnal schedules from building energy interval data

Saurabh Jalori, T Agami Reddy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

Inverse statistical methods to analyze utility billing data and/or hourly/daily monitored energy consumption data are being increasingly adopted by building professionals engaged in improving the energy efficiency of existing buildings. The field is quite mature but still evolving as it adapts to the surge of energy interval data provided by smart meters. For example, many of the simpler physics-based models relying on regression methods are being enhanced by the use of machine learning or data mining techniques coupled with knowledge bases of energy use data from different generic building types and other types of data streams. Although quite sophisticated, the published literature seems lacking in robust and sensitive methods to perform some of the simpler analysis tasks. Two such tasks are related to the automated identification and removal of outlier data points during days when the building is operated abnormally, and to the identification of day types or, more correctly, to the identification of a parsimonious set of building operational and occupancy schedules. This paper proposes a methodology to perform those tasks (which can be automated) using robust techniques borrowed from the data mining literature. These tasks are essential if one wishes to subsequently use the data to operate the buildings more efficiently - for example, to identify baseline models, to perform condition monitoring, or for short-term load prediction for demand response programs. Such issues are addressed in a companion paper (Jalori and Reddy 2015). The application of the proposed methodology is illustrated using two different buildings, one synthetic (the U.S. Department of Energy (DOE) medium-office prototype) building and another, an actual office building.

Original languageEnglish (US)
Title of host publicationASHRAE Transactions
PublisherAmer. Soc. Heating, Ref. Air-Conditoning Eng. Inc.
Pages33-44
Number of pages12
Volume121
ISBN (Print)9781939200013
StatePublished - 2015
Event2015 ASHRAE Annual Conference - Atlanta, United States
Duration: Jun 27 2015Jul 1 2015

Other

Other2015 ASHRAE Annual Conference
CountryUnited States
CityAtlanta
Period6/27/157/1/15

Fingerprint

Office buildings
Data mining
Smart meters
Condition monitoring
Energy efficiency
Learning systems
Statistical methods
Energy utilization
Physics

ASJC Scopus subject areas

  • Mechanical Engineering
  • Building and Construction

Cite this

Jalori, S., & Reddy, T. A. (2015). A new clustering method to identify outliers and diurnal schedules from building energy interval data. In ASHRAE Transactions (Vol. 121, pp. 33-44). Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc..

A new clustering method to identify outliers and diurnal schedules from building energy interval data. / Jalori, Saurabh; Reddy, T Agami.

ASHRAE Transactions. Vol. 121 Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc., 2015. p. 33-44.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jalori, S & Reddy, TA 2015, A new clustering method to identify outliers and diurnal schedules from building energy interval data. in ASHRAE Transactions. vol. 121, Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc., pp. 33-44, 2015 ASHRAE Annual Conference, Atlanta, United States, 6/27/15.
Jalori S, Reddy TA. A new clustering method to identify outliers and diurnal schedules from building energy interval data. In ASHRAE Transactions. Vol. 121. Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc. 2015. p. 33-44
Jalori, Saurabh ; Reddy, T Agami. / A new clustering method to identify outliers and diurnal schedules from building energy interval data. ASHRAE Transactions. Vol. 121 Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc., 2015. pp. 33-44
@inproceedings{eb2c4847e72840a3a8a1b02befc1c7aa,
title = "A new clustering method to identify outliers and diurnal schedules from building energy interval data",
abstract = "Inverse statistical methods to analyze utility billing data and/or hourly/daily monitored energy consumption data are being increasingly adopted by building professionals engaged in improving the energy efficiency of existing buildings. The field is quite mature but still evolving as it adapts to the surge of energy interval data provided by smart meters. For example, many of the simpler physics-based models relying on regression methods are being enhanced by the use of machine learning or data mining techniques coupled with knowledge bases of energy use data from different generic building types and other types of data streams. Although quite sophisticated, the published literature seems lacking in robust and sensitive methods to perform some of the simpler analysis tasks. Two such tasks are related to the automated identification and removal of outlier data points during days when the building is operated abnormally, and to the identification of day types or, more correctly, to the identification of a parsimonious set of building operational and occupancy schedules. This paper proposes a methodology to perform those tasks (which can be automated) using robust techniques borrowed from the data mining literature. These tasks are essential if one wishes to subsequently use the data to operate the buildings more efficiently - for example, to identify baseline models, to perform condition monitoring, or for short-term load prediction for demand response programs. Such issues are addressed in a companion paper (Jalori and Reddy 2015). The application of the proposed methodology is illustrated using two different buildings, one synthetic (the U.S. Department of Energy (DOE) medium-office prototype) building and another, an actual office building.",
author = "Saurabh Jalori and Reddy, {T Agami}",
year = "2015",
language = "English (US)",
isbn = "9781939200013",
volume = "121",
pages = "33--44",
booktitle = "ASHRAE Transactions",
publisher = "Amer. Soc. Heating, Ref. Air-Conditoning Eng. Inc.",

}

TY - GEN

T1 - A new clustering method to identify outliers and diurnal schedules from building energy interval data

AU - Jalori, Saurabh

AU - Reddy, T Agami

PY - 2015

Y1 - 2015

N2 - Inverse statistical methods to analyze utility billing data and/or hourly/daily monitored energy consumption data are being increasingly adopted by building professionals engaged in improving the energy efficiency of existing buildings. The field is quite mature but still evolving as it adapts to the surge of energy interval data provided by smart meters. For example, many of the simpler physics-based models relying on regression methods are being enhanced by the use of machine learning or data mining techniques coupled with knowledge bases of energy use data from different generic building types and other types of data streams. Although quite sophisticated, the published literature seems lacking in robust and sensitive methods to perform some of the simpler analysis tasks. Two such tasks are related to the automated identification and removal of outlier data points during days when the building is operated abnormally, and to the identification of day types or, more correctly, to the identification of a parsimonious set of building operational and occupancy schedules. This paper proposes a methodology to perform those tasks (which can be automated) using robust techniques borrowed from the data mining literature. These tasks are essential if one wishes to subsequently use the data to operate the buildings more efficiently - for example, to identify baseline models, to perform condition monitoring, or for short-term load prediction for demand response programs. Such issues are addressed in a companion paper (Jalori and Reddy 2015). The application of the proposed methodology is illustrated using two different buildings, one synthetic (the U.S. Department of Energy (DOE) medium-office prototype) building and another, an actual office building.

AB - Inverse statistical methods to analyze utility billing data and/or hourly/daily monitored energy consumption data are being increasingly adopted by building professionals engaged in improving the energy efficiency of existing buildings. The field is quite mature but still evolving as it adapts to the surge of energy interval data provided by smart meters. For example, many of the simpler physics-based models relying on regression methods are being enhanced by the use of machine learning or data mining techniques coupled with knowledge bases of energy use data from different generic building types and other types of data streams. Although quite sophisticated, the published literature seems lacking in robust and sensitive methods to perform some of the simpler analysis tasks. Two such tasks are related to the automated identification and removal of outlier data points during days when the building is operated abnormally, and to the identification of day types or, more correctly, to the identification of a parsimonious set of building operational and occupancy schedules. This paper proposes a methodology to perform those tasks (which can be automated) using robust techniques borrowed from the data mining literature. These tasks are essential if one wishes to subsequently use the data to operate the buildings more efficiently - for example, to identify baseline models, to perform condition monitoring, or for short-term load prediction for demand response programs. Such issues are addressed in a companion paper (Jalori and Reddy 2015). The application of the proposed methodology is illustrated using two different buildings, one synthetic (the U.S. Department of Energy (DOE) medium-office prototype) building and another, an actual office building.

UR - http://www.scopus.com/inward/record.url?scp=84960903683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84960903683&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781939200013

VL - 121

SP - 33

EP - 44

BT - ASHRAE Transactions

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

ER -