Exploration of the Bayesian Network framework for modelling window control behaviour

Verena M. Barthelmes, Yeonsook Heo, Valentina Fabi, Stefano P. Corgnati

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Extended literature reviews confirm that the accurate evaluation of energy-related occupant behaviour is a key factor for bridging the gap between predicted and actual energy performance of buildings. One of the key energy-related human behaviours is window control behaviour that has been modelled by different probabilistic modelling approaches. In recent years, Bayesian Networks (BNs) have become a popular representation based on graphical models for modelling stochastic processes with consideration of uncertainty in various fields, from computational biology to complex engineering problems. This study investigates the potential applicability of BNs to capture underlying complicated relationships between various influencing factors and energy-related behavioural actions of occupants in buildings: in particular, window opening/closing behaviour of occupants in residential buildings is investigated. This study addresses five key research questions related to modelling window control behaviour: (A) variable selection for identifying key drivers impacting window control behaviour, (B) correlations between key variables for structuring a statistical model, (C) target definition for finding the most suitable target variable, (D) BN model with capabilities to treat mixed data, and (E) validation of a stochastic BN model. A case study on the basis of measured data in one residential apartment located in Copenhagen, Denmark provides key findings associated with the five research questions through the modelling process of developing the BN model.

Original languageEnglish
Pages (from-to)318-330
Number of pages13
JournalBuilding and Environment
Volume126
DOIs
Publication statusPublished - 2017 Dec 1
Externally publishedYes

Fingerprint

behavior control
Bayesian networks
energy
modeling
building
residential building
human behavior
apartment
Plant shutdowns
stochasticity
Random processes
literature review
Denmark
biology
driver
uncertainty
engineering
evaluation
performance

Keywords

  • Bayesian networks
  • Occupant behaviour
  • Stochastic modelling
  • Window control behaviour

ASJC Scopus subject areas

  • Environmental Engineering
  • Civil and Structural Engineering
  • Geography, Planning and Development
  • Building and Construction

Cite this

Exploration of the Bayesian Network framework for modelling window control behaviour. / Barthelmes, Verena M.; Heo, Yeonsook; Fabi, Valentina; Corgnati, Stefano P.

In: Building and Environment, Vol. 126, 01.12.2017, p. 318-330.

Research output: Contribution to journalArticle

Barthelmes, Verena M. ; Heo, Yeonsook ; Fabi, Valentina ; Corgnati, Stefano P. / Exploration of the Bayesian Network framework for modelling window control behaviour. In: Building and Environment. 2017 ; Vol. 126. pp. 318-330.
@article{b121c49debf3401cbd06d88d93db73a3,
title = "Exploration of the Bayesian Network framework for modelling window control behaviour",
abstract = "Extended literature reviews confirm that the accurate evaluation of energy-related occupant behaviour is a key factor for bridging the gap between predicted and actual energy performance of buildings. One of the key energy-related human behaviours is window control behaviour that has been modelled by different probabilistic modelling approaches. In recent years, Bayesian Networks (BNs) have become a popular representation based on graphical models for modelling stochastic processes with consideration of uncertainty in various fields, from computational biology to complex engineering problems. This study investigates the potential applicability of BNs to capture underlying complicated relationships between various influencing factors and energy-related behavioural actions of occupants in buildings: in particular, window opening/closing behaviour of occupants in residential buildings is investigated. This study addresses five key research questions related to modelling window control behaviour: (A) variable selection for identifying key drivers impacting window control behaviour, (B) correlations between key variables for structuring a statistical model, (C) target definition for finding the most suitable target variable, (D) BN model with capabilities to treat mixed data, and (E) validation of a stochastic BN model. A case study on the basis of measured data in one residential apartment located in Copenhagen, Denmark provides key findings associated with the five research questions through the modelling process of developing the BN model.",
keywords = "Bayesian networks, Occupant behaviour, Stochastic modelling, Window control behaviour",
author = "Barthelmes, {Verena M.} and Yeonsook Heo and Valentina Fabi and Corgnati, {Stefano P.}",
year = "2017",
month = "12",
day = "1",
doi = "10.1016/j.buildenv.2017.10.011",
language = "English",
volume = "126",
pages = "318--330",
journal = "Building and Environment",
issn = "0360-1323",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Exploration of the Bayesian Network framework for modelling window control behaviour

AU - Barthelmes, Verena M.

AU - Heo, Yeonsook

AU - Fabi, Valentina

AU - Corgnati, Stefano P.

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Extended literature reviews confirm that the accurate evaluation of energy-related occupant behaviour is a key factor for bridging the gap between predicted and actual energy performance of buildings. One of the key energy-related human behaviours is window control behaviour that has been modelled by different probabilistic modelling approaches. In recent years, Bayesian Networks (BNs) have become a popular representation based on graphical models for modelling stochastic processes with consideration of uncertainty in various fields, from computational biology to complex engineering problems. This study investigates the potential applicability of BNs to capture underlying complicated relationships between various influencing factors and energy-related behavioural actions of occupants in buildings: in particular, window opening/closing behaviour of occupants in residential buildings is investigated. This study addresses five key research questions related to modelling window control behaviour: (A) variable selection for identifying key drivers impacting window control behaviour, (B) correlations between key variables for structuring a statistical model, (C) target definition for finding the most suitable target variable, (D) BN model with capabilities to treat mixed data, and (E) validation of a stochastic BN model. A case study on the basis of measured data in one residential apartment located in Copenhagen, Denmark provides key findings associated with the five research questions through the modelling process of developing the BN model.

AB - Extended literature reviews confirm that the accurate evaluation of energy-related occupant behaviour is a key factor for bridging the gap between predicted and actual energy performance of buildings. One of the key energy-related human behaviours is window control behaviour that has been modelled by different probabilistic modelling approaches. In recent years, Bayesian Networks (BNs) have become a popular representation based on graphical models for modelling stochastic processes with consideration of uncertainty in various fields, from computational biology to complex engineering problems. This study investigates the potential applicability of BNs to capture underlying complicated relationships between various influencing factors and energy-related behavioural actions of occupants in buildings: in particular, window opening/closing behaviour of occupants in residential buildings is investigated. This study addresses five key research questions related to modelling window control behaviour: (A) variable selection for identifying key drivers impacting window control behaviour, (B) correlations between key variables for structuring a statistical model, (C) target definition for finding the most suitable target variable, (D) BN model with capabilities to treat mixed data, and (E) validation of a stochastic BN model. A case study on the basis of measured data in one residential apartment located in Copenhagen, Denmark provides key findings associated with the five research questions through the modelling process of developing the BN model.

KW - Bayesian networks

KW - Occupant behaviour

KW - Stochastic modelling

KW - Window control behaviour

UR - http://www.scopus.com/inward/record.url?scp=85033562421&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85033562421&partnerID=8YFLogxK

U2 - 10.1016/j.buildenv.2017.10.011

DO - 10.1016/j.buildenv.2017.10.011

M3 - Article

AN - SCOPUS:85033562421

VL - 126

SP - 318

EP - 330

JO - Building and Environment

JF - Building and Environment

SN - 0360-1323

ER -