Hidden Markov Models for indirect classification of occupant behaviour

Jon Anders Reichert Liisberg, Jan Kloppenborg Møller, H. Bloem, J. Cipriano, G. Mor, Henrik Madsen

Research output: Contribution to journalJournal articleResearchpeer-review

253 Downloads (Pure)

Abstract

Even for similar residential buildings, a huge variability in the energy consumption can be observed. This variability is mainly due to the different behaviours of the occupants and this impacts the thermal (temperature setting, window opening, etc.) as well as the electrical (appliances, TV, computer, etc.) consumption.

It is very seldom to find direct observations of occupant presence and behaviour in residential buildings. However, given the increasing use of smart metering, the opportunity and potential for indirect observation and classification of occupants’ behaviour is possible. This paper focuses on the use of Hidden Markov Models (HMMs) to create methods for indirect observations and characterisation of occupant behaviour.

By applying homogeneous HMMs on the electricity consumption of fourteen apartments, three states describing the data were found suitable. The most likely sequence of states was determined (global decoding). From reconstruction of the states, dependencies like ambient air temperature were investigated. Combined with an occupant survey, this was used to classify/interpret the states as (1) absent or asleep, (2) home, medium consumption and (3) home, high consumption. From the global decoding, the average probability profiles with respect to time of day were investigated, and four distinct patterns of occupant behaviour were observed. Based on the initial results of the homogeneous HMMs and with the observed dependencies, time dependent HMMs (inhomogeneous HMMs) were developed, which improved forecasting. For both the homogeneous and inhomogeneous HMMs, indications of common parameters were observed, which suggests further development of the HMMs as population models.
Original languageEnglish
JournalSustainable Cities and Society
Volume27
Pages (from-to)83-98
ISSN2210-6707
DOIs
Publication statusPublished - 2016

Keywords

  • Occupant behaviour
  • Indirect classification
  • Hidden Markov Models

Cite this

Liisberg, Jon Anders Reichert ; Møller, Jan Kloppenborg ; Bloem, H. ; Cipriano, J. ; Mor, G. ; Madsen, Henrik. / Hidden Markov Models for indirect classification of occupant behaviour. In: Sustainable Cities and Society. 2016 ; Vol. 27. pp. 83-98.
@article{287cd6abd6a9410dad73407fb3b0b0ee,
title = "Hidden Markov Models for indirect classification of occupant behaviour",
abstract = "Even for similar residential buildings, a huge variability in the energy consumption can be observed. This variability is mainly due to the different behaviours of the occupants and this impacts the thermal (temperature setting, window opening, etc.) as well as the electrical (appliances, TV, computer, etc.) consumption. It is very seldom to find direct observations of occupant presence and behaviour in residential buildings. However, given the increasing use of smart metering, the opportunity and potential for indirect observation and classification of occupants’ behaviour is possible. This paper focuses on the use of Hidden Markov Models (HMMs) to create methods for indirect observations and characterisation of occupant behaviour. By applying homogeneous HMMs on the electricity consumption of fourteen apartments, three states describing the data were found suitable. The most likely sequence of states was determined (global decoding). From reconstruction of the states, dependencies like ambient air temperature were investigated. Combined with an occupant survey, this was used to classify/interpret the states as (1) absent or asleep, (2) home, medium consumption and (3) home, high consumption. From the global decoding, the average probability profiles with respect to time of day were investigated, and four distinct patterns of occupant behaviour were observed. Based on the initial results of the homogeneous HMMs and with the observed dependencies, time dependent HMMs (inhomogeneous HMMs) were developed, which improved forecasting. For both the homogeneous and inhomogeneous HMMs, indications of common parameters were observed, which suggests further development of the HMMs as population models.",
keywords = "Occupant behaviour, Indirect classification, Hidden Markov Models",
author = "Liisberg, {Jon Anders Reichert} and M{\o}ller, {Jan Kloppenborg} and H. Bloem and J. Cipriano and G. Mor and Henrik Madsen",
year = "2016",
doi = "10.1016/j.scs.2016.07.001",
language = "English",
volume = "27",
pages = "83--98",
journal = "Sustainable Cities and Society",
issn = "2210-6707",
publisher = "Elsevier",

}

Hidden Markov Models for indirect classification of occupant behaviour. / Liisberg, Jon Anders Reichert; Møller, Jan Kloppenborg; Bloem, H.; Cipriano, J.; Mor, G.; Madsen, Henrik.

In: Sustainable Cities and Society, Vol. 27, 2016, p. 83-98.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Hidden Markov Models for indirect classification of occupant behaviour

AU - Liisberg, Jon Anders Reichert

AU - Møller, Jan Kloppenborg

AU - Bloem, H.

AU - Cipriano, J.

AU - Mor, G.

AU - Madsen, Henrik

PY - 2016

Y1 - 2016

N2 - Even for similar residential buildings, a huge variability in the energy consumption can be observed. This variability is mainly due to the different behaviours of the occupants and this impacts the thermal (temperature setting, window opening, etc.) as well as the electrical (appliances, TV, computer, etc.) consumption. It is very seldom to find direct observations of occupant presence and behaviour in residential buildings. However, given the increasing use of smart metering, the opportunity and potential for indirect observation and classification of occupants’ behaviour is possible. This paper focuses on the use of Hidden Markov Models (HMMs) to create methods for indirect observations and characterisation of occupant behaviour. By applying homogeneous HMMs on the electricity consumption of fourteen apartments, three states describing the data were found suitable. The most likely sequence of states was determined (global decoding). From reconstruction of the states, dependencies like ambient air temperature were investigated. Combined with an occupant survey, this was used to classify/interpret the states as (1) absent or asleep, (2) home, medium consumption and (3) home, high consumption. From the global decoding, the average probability profiles with respect to time of day were investigated, and four distinct patterns of occupant behaviour were observed. Based on the initial results of the homogeneous HMMs and with the observed dependencies, time dependent HMMs (inhomogeneous HMMs) were developed, which improved forecasting. For both the homogeneous and inhomogeneous HMMs, indications of common parameters were observed, which suggests further development of the HMMs as population models.

AB - Even for similar residential buildings, a huge variability in the energy consumption can be observed. This variability is mainly due to the different behaviours of the occupants and this impacts the thermal (temperature setting, window opening, etc.) as well as the electrical (appliances, TV, computer, etc.) consumption. It is very seldom to find direct observations of occupant presence and behaviour in residential buildings. However, given the increasing use of smart metering, the opportunity and potential for indirect observation and classification of occupants’ behaviour is possible. This paper focuses on the use of Hidden Markov Models (HMMs) to create methods for indirect observations and characterisation of occupant behaviour. By applying homogeneous HMMs on the electricity consumption of fourteen apartments, three states describing the data were found suitable. The most likely sequence of states was determined (global decoding). From reconstruction of the states, dependencies like ambient air temperature were investigated. Combined with an occupant survey, this was used to classify/interpret the states as (1) absent or asleep, (2) home, medium consumption and (3) home, high consumption. From the global decoding, the average probability profiles with respect to time of day were investigated, and four distinct patterns of occupant behaviour were observed. Based on the initial results of the homogeneous HMMs and with the observed dependencies, time dependent HMMs (inhomogeneous HMMs) were developed, which improved forecasting. For both the homogeneous and inhomogeneous HMMs, indications of common parameters were observed, which suggests further development of the HMMs as population models.

KW - Occupant behaviour

KW - Indirect classification

KW - Hidden Markov Models

U2 - 10.1016/j.scs.2016.07.001

DO - 10.1016/j.scs.2016.07.001

M3 - Journal article

VL - 27

SP - 83

EP - 98

JO - Sustainable Cities and Society

JF - Sustainable Cities and Society

SN - 2210-6707

ER -