An ensemble learning framework for anomaly detection in building energy consumption

During building operation, a significant amount of energy is wasted due to equipment and human-related faults. To reduce waste, today's smart buildings monitor energy usage with the aim of identifying abnormal consumption behaviour and notifying the building manager to implement appropriate ene...

Full description

Saved in:
Bibliographic Details
Published in:Energy and buildings Vol. 144; pp. 191 - 206
Main Authors: Araya, Daniel B., Grolinger, Katarina, ElYamany, Hany F., Capretz, Miriam A.M., Bitsuamlak, Girma
Format: Journal Article
Language:English
Published: Lausanne Elsevier B.V 01.06.2017
Elsevier BV
Subjects:
Alarm systems
Anomalies
Anomaly detection
Autoencoder
Building automation
Building energy consumption
Classifiers
Consumption patterns
Energy conservation
Energy consumption
Energy efficiency
Energy usage
Ensemble learning
Fault diagnosis
Faults
Random forest
Sliding
Smart buildings
Support vector regression
Canada
Brampton Ontario Canada
Support vector regression
Random forest
Building energy consumption
Ensemble learning
Autoencoder
Anomaly detection
ISSN:0378-7788, 1872-6178
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:During building operation, a significant amount of energy is wasted due to equipment and human-related faults. To reduce waste, today's smart buildings monitor energy usage with the aim of identifying abnormal consumption behaviour and notifying the building manager to implement appropriate energy-saving procedures. To this end, this research proposes a new pattern-based anomaly classifier, the collective contextual anomaly detection using sliding window (CCAD-SW) framework. The CCAD-SW framework identifies anomalous consumption patterns using overlapping sliding windows. To enhance the anomaly detection capacity of the CCAD-SW, this research also proposes the ensemble anomaly detection (EAD) framework. The EAD is a generic framework that combines several anomaly detection classifiers using majority voting. To ensure diversity of anomaly classifiers, the EAD is implemented by combining pattern-based (e.g., CCAD-SW) and prediction-based anomaly classifiers. The research was evaluated using real-world data provided by Powersmiths, located in Brampton, Ontario, Canada. Results show that the EAD framework improved the sensitivity of the CCAD-SW by 3.6% and reduced false alarm rate by 2.7%.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0378-7788
1872-6178
DOI:10.1016/j.enbuild.2017.02.058