Consensus-Based Method for Anomaly Detection in VAV Units

Claudio Giovanni Mattera*, Hamid Reza Shaker, Muhyiddine Jradi

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

53 Downloads (Pure)

Abstract

Buildings account for large part of global energy consumption. Besides energy consumed due to normal operation, a large amount of energy can be wasted due to faults in buildings subsystems. Fault detection and diagnostics techniques aim to identify faults and prevent energy waste, but are often difficult to apply in practice. Data-driven methods, in particular, require an adequate amount of fault-free training data, which is rarely available. In this paper, we propose a method for anomaly detection that exploits consensus among multiple identical components. Even if some of the components are faulty, their aggregate behaviour is overall correct, and it can be used to train a data-driven model. We test our method on variable-air-volume units in an existing building, executing two experiments grouping the components according to ventilation unit, and according to room type. The two experiments identified the same set of anomalous components, i.e., their behaviour was different from the rest of the group in both cases, and this suggests that the anomaly was not due to wrong group assignment. The proposed method shows the potential of exploiting consensus among multiple identical systems to detect anomalous ones
Original languageEnglish
Article number468
JournalEnergies
Volume12
Issue number3
Number of pages17
ISSN1996-1073
DOIs
Publication statusPublished - 1. Feb 2019

Fingerprint

Anomaly Detection
Fault
Unit
Fault detection
Data-driven
Methods on variables
Ventilation
Anomalous
Energy utilization
Energy
Experiments
Fault Detection
Air
Grouping
Anomaly
Energy Consumption
Experiment
Diagnostics
Subsystem
Assignment

Keywords

  • Consensus
  • Fault detection and diagnosis
  • Smart buildings

Cite this

@article{3ce3119830464d1abff4947d97eb5b91,
title = "Consensus-Based Method for Anomaly Detection in VAV Units",
abstract = "Buildings account for large part of global energy consumption. Besides energy consumed due to normal operation, a large amount of energy can be wasted due to faults in buildings subsystems. Fault detection and diagnostics techniques aim to identify faults and prevent energy waste, but are often difficult to apply in practice. Data-driven methods, in particular, require an adequate amount of fault-free training data, which is rarely available. In this paper, we propose a method for anomaly detection that exploits consensus among multiple identical components. Even if some of the components are faulty, their aggregate behaviour is overall correct, and it can be used to train a data-driven model. We test our method on variable-air-volume units in an existing building, executing two experiments grouping the components according to ventilation unit, and according to room type. The two experiments identified the same set of anomalous components, i.e., their behaviour was different from the rest of the group in both cases, and this suggests that the anomaly was not due to wrong group assignment. The proposed method shows the potential of exploiting consensus among multiple identical systems to detect anomalous ones",
keywords = "Consensus, Fault detection and diagnosis, Smart buildings",
author = "Mattera, {Claudio Giovanni} and Shaker, {Hamid Reza} and Muhyiddine Jradi",
year = "2019",
month = "2",
day = "1",
doi = "10.3390/en12030468",
language = "English",
volume = "12",
journal = "Energies",
issn = "1996-1073",
publisher = "MDPI",
number = "3",

}

Consensus-Based Method for Anomaly Detection in VAV Units. / Mattera, Claudio Giovanni; Shaker, Hamid Reza; Jradi, Muhyiddine.

In: Energies, Vol. 12, No. 3, 468, 01.02.2019.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Consensus-Based Method for Anomaly Detection in VAV Units

AU - Mattera, Claudio Giovanni

AU - Shaker, Hamid Reza

AU - Jradi, Muhyiddine

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Buildings account for large part of global energy consumption. Besides energy consumed due to normal operation, a large amount of energy can be wasted due to faults in buildings subsystems. Fault detection and diagnostics techniques aim to identify faults and prevent energy waste, but are often difficult to apply in practice. Data-driven methods, in particular, require an adequate amount of fault-free training data, which is rarely available. In this paper, we propose a method for anomaly detection that exploits consensus among multiple identical components. Even if some of the components are faulty, their aggregate behaviour is overall correct, and it can be used to train a data-driven model. We test our method on variable-air-volume units in an existing building, executing two experiments grouping the components according to ventilation unit, and according to room type. The two experiments identified the same set of anomalous components, i.e., their behaviour was different from the rest of the group in both cases, and this suggests that the anomaly was not due to wrong group assignment. The proposed method shows the potential of exploiting consensus among multiple identical systems to detect anomalous ones

AB - Buildings account for large part of global energy consumption. Besides energy consumed due to normal operation, a large amount of energy can be wasted due to faults in buildings subsystems. Fault detection and diagnostics techniques aim to identify faults and prevent energy waste, but are often difficult to apply in practice. Data-driven methods, in particular, require an adequate amount of fault-free training data, which is rarely available. In this paper, we propose a method for anomaly detection that exploits consensus among multiple identical components. Even if some of the components are faulty, their aggregate behaviour is overall correct, and it can be used to train a data-driven model. We test our method on variable-air-volume units in an existing building, executing two experiments grouping the components according to ventilation unit, and according to room type. The two experiments identified the same set of anomalous components, i.e., their behaviour was different from the rest of the group in both cases, and this suggests that the anomaly was not due to wrong group assignment. The proposed method shows the potential of exploiting consensus among multiple identical systems to detect anomalous ones

KW - Consensus

KW - Fault detection and diagnosis

KW - Smart buildings

U2 - 10.3390/en12030468

DO - 10.3390/en12030468

M3 - Journal article

VL - 12

JO - Energies

JF - Energies

SN - 1996-1073

IS - 3

M1 - 468

ER -