Anomaly detection of building systems using energy demand frequency domain analysis

Michael Wrinch; Tarek H.M. El-Fouly; Steven Wong

doi:10.1109/PESGM.2012.6344790

Anomaly detection of building systems using energy demand frequency domain analysis

Michael Wrinch
, Tarek H.M. El-Fouly
, Steven Wong

Electrical Engineering

Hedgehog Technologies Inc.
Natural Resources Canada (NRCan)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

23 Scopus citations

Abstract

This paper presents and demonstrates a method to quickly identify when regular periodic activities, such as a daily night setback on a thermostat, are inappropriately configured or accidentally reset. Anomalies in periodic building operations are identified by analyzing smart meter electrical demand data in the frequency domain with a weekly travelling time window instead of using time domain functions such as load factor. Initial experiments on a real site found that spectral energy signals for periodic (frequency) hours of 4, 6, 8, 12 and days 1, 3.5 and 7 to be greatly reduced when a device is not functioning appropriately. In addition, the ratio of the DC offset (0 Hz) energy with the other higher periodic energies can normalize the periodic energies to a relative index that can then be used for comparing other seasons and other buildings for periodical performance.

Original language	British English
Title of host publication	2012 IEEE Power and Energy Society General Meeting, PES 2012
DOIs	https://doi.org/10.1109/PESGM.2012.6344790
State	Published - 2012
Event	2012 IEEE Power and Energy Society General Meeting, PES 2012 - San Diego, CA, United States Duration: 22 Jul 2012 → 26 Jul 2012

Publication series

Name	IEEE Power and Energy Society General Meeting
ISSN (Print)	1944-9925
ISSN (Electronic)	1944-9933

Conference

Conference	2012 IEEE Power and Energy Society General Meeting, PES 2012
Country/Territory	United States
City	San Diego, CA
Period	22/07/12 → 26/07/12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Energy conservation
Energy efficiency
Energy management
Load management
Power system measurements
Smart grids

Access to Document

10.1109/PESGM.2012.6344790

OpenUrl availability

Full text

Cite this

@inproceedings{d201a64d61aa4a4f8ba69e6ad64fd3b5,

title = "Anomaly detection of building systems using energy demand frequency domain analysis",

abstract = "This paper presents and demonstrates a method to quickly identify when regular periodic activities, such as a daily night setback on a thermostat, are inappropriately configured or accidentally reset. Anomalies in periodic building operations are identified by analyzing smart meter electrical demand data in the frequency domain with a weekly travelling time window instead of using time domain functions such as load factor. Initial experiments on a real site found that spectral energy signals for periodic (frequency) hours of 4, 6, 8, 12 and days 1, 3.5 and 7 to be greatly reduced when a device is not functioning appropriately. In addition, the ratio of the DC offset (0 Hz) energy with the other higher periodic energies can normalize the periodic energies to a relative index that can then be used for comparing other seasons and other buildings for periodical performance.",

keywords = "Energy conservation, Energy efficiency, Energy management, Load management, Power system measurements, Smart grids",

author = "Michael Wrinch and El-Fouly, \{Tarek H.M.\} and Steven Wong",

year = "2012",

doi = "10.1109/PESGM.2012.6344790",

language = "British English",

isbn = "9781467327275",

series = "IEEE Power and Energy Society General Meeting",

booktitle = "2012 IEEE Power and Energy Society General Meeting, PES 2012",

note = "2012 IEEE Power and Energy Society General Meeting, PES 2012 ; Conference date: 22-07-2012 Through 26-07-2012",

}

Wrinch, M, El-Fouly, THM & Wong, S 2012, Anomaly detection of building systems using energy demand frequency domain analysis. in 2012 IEEE Power and Energy Society General Meeting, PES 2012., 6344790, IEEE Power and Energy Society General Meeting, 2012 IEEE Power and Energy Society General Meeting, PES 2012, San Diego, CA, United States, 22/07/12. https://doi.org/10.1109/PESGM.2012.6344790

TY - GEN

T1 - Anomaly detection of building systems using energy demand frequency domain analysis

AU - Wrinch, Michael

AU - El-Fouly, Tarek H.M.

AU - Wong, Steven

PY - 2012

Y1 - 2012

N2 - This paper presents and demonstrates a method to quickly identify when regular periodic activities, such as a daily night setback on a thermostat, are inappropriately configured or accidentally reset. Anomalies in periodic building operations are identified by analyzing smart meter electrical demand data in the frequency domain with a weekly travelling time window instead of using time domain functions such as load factor. Initial experiments on a real site found that spectral energy signals for periodic (frequency) hours of 4, 6, 8, 12 and days 1, 3.5 and 7 to be greatly reduced when a device is not functioning appropriately. In addition, the ratio of the DC offset (0 Hz) energy with the other higher periodic energies can normalize the periodic energies to a relative index that can then be used for comparing other seasons and other buildings for periodical performance.

AB - This paper presents and demonstrates a method to quickly identify when regular periodic activities, such as a daily night setback on a thermostat, are inappropriately configured or accidentally reset. Anomalies in periodic building operations are identified by analyzing smart meter electrical demand data in the frequency domain with a weekly travelling time window instead of using time domain functions such as load factor. Initial experiments on a real site found that spectral energy signals for periodic (frequency) hours of 4, 6, 8, 12 and days 1, 3.5 and 7 to be greatly reduced when a device is not functioning appropriately. In addition, the ratio of the DC offset (0 Hz) energy with the other higher periodic energies can normalize the periodic energies to a relative index that can then be used for comparing other seasons and other buildings for periodical performance.

KW - Energy conservation

KW - Energy efficiency

KW - Energy management

KW - Load management

KW - Power system measurements

KW - Smart grids

UR - https://www.scopus.com/pages/publications/84870582055

U2 - 10.1109/PESGM.2012.6344790

DO - 10.1109/PESGM.2012.6344790

M3 - Conference contribution

AN - SCOPUS:84870582055

SN - 9781467327275

T3 - IEEE Power and Energy Society General Meeting

BT - 2012 IEEE Power and Energy Society General Meeting, PES 2012

T2 - 2012 IEEE Power and Energy Society General Meeting, PES 2012

Y2 - 22 July 2012 through 26 July 2012

ER -

Anomaly detection of building systems using energy demand frequency domain analysis

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this