• 3 Citations

Abstract

There is a growing desire to measure the operational performance of buildings – often many buildings simultaneously – but the cost of sensors and complexity of deployment is a significant constraint. In this paper, we present an approach to minimising the cost of sensing by recognising that researchers are often not interested in the raw data itself but rather some inferred performance metric (e.g. high CO2 levels may indicate poor ventilation). We cast the problem as one of constrained optimisation – specifically, as a bounded knapsack problem (BKP) – to choose the best sensors for the set given each sensor's predictive value and cost. Training data is obtained from a field study comprising a wide range of possible sensors from which a minimum set can be extracted. We validate the method using reliable self-reported event diaries as a measure of actual performance. Results show that the method produces sensors sets that are good predictors of performance and the optimal sets vary substantially with the constraint parameters. Furthermore, valuable yet expensive sensors are often not chosen in the optimal set due to strong co-incidence of sensor signals. For example, light level and sound level often increase at the same time. The overall implication of the work is that a large number of co-incident low-cost sensors can be used to build up a picture of building performance, without significantly compromising information content, and this could have major benefits for the smart metering industry.
LanguageEnglish
Pages11-22
JournalBuilding and Environment
Volume110
Early online date8 Sep 2016
DOIs
StatusPublished - 1 Dec 2016

Fingerprint

building
sensor
energy
event
Sensors
performance
costs
cost
information content
Costs
incident
incidence
Constrained optimization
industry
Ventilation
ventilation
Acoustic waves
Industry

Cite this

Designing sensor sets for capturing energy events in buildings. / Lovett, Thomas; Lee, Jeehang; Thomas, Elizabeth; Natarajan, Sukumar; Brown, Matthew; Padget, Julian; Coley, David.

In: Building and Environment, Vol. 110, 01.12.2016, p. 11-22.

Research output: Contribution to journalArticle

Lovett, Thomas ; Lee, Jeehang ; Thomas, Elizabeth ; Natarajan, Sukumar ; Brown, Matthew ; Padget, Julian ; Coley, David. / Designing sensor sets for capturing energy events in buildings. In: Building and Environment. 2016 ; Vol. 110. pp. 11-22.
@article{b41cfc3fd301420fb1b9bc69a252fc60,
title = "Designing sensor sets for capturing energy events in buildings",
abstract = "There is a growing desire to measure the operational performance of buildings – often many buildings simultaneously – but the cost of sensors and complexity of deployment is a significant constraint. In this paper, we present an approach to minimising the cost of sensing by recognising that researchers are often not interested in the raw data itself but rather some inferred performance metric (e.g. high CO2 levels may indicate poor ventilation). We cast the problem as one of constrained optimisation – specifically, as a bounded knapsack problem (BKP) – to choose the best sensors for the set given each sensor's predictive value and cost. Training data is obtained from a field study comprising a wide range of possible sensors from which a minimum set can be extracted. We validate the method using reliable self-reported event diaries as a measure of actual performance. Results show that the method produces sensors sets that are good predictors of performance and the optimal sets vary substantially with the constraint parameters. Furthermore, valuable yet expensive sensors are often not chosen in the optimal set due to strong co-incidence of sensor signals. For example, light level and sound level often increase at the same time. The overall implication of the work is that a large number of co-incident low-cost sensors can be used to build up a picture of building performance, without significantly compromising information content, and this could have major benefits for the smart metering industry.",
author = "Thomas Lovett and Jeehang Lee and Elizabeth Thomas and Sukumar Natarajan and Matthew Brown and Julian Padget and David Coley",
year = "2016",
month = "12",
day = "1",
doi = "10.1016/j.buildenv.2016.09.004",
language = "English",
volume = "110",
pages = "11--22",
journal = "Building and Environment",
issn = "0360-1323",
publisher = "Elsevier",

}

TY - JOUR

T1 - Designing sensor sets for capturing energy events in buildings

AU - Lovett, Thomas

AU - Lee, Jeehang

AU - Thomas, Elizabeth

AU - Natarajan, Sukumar

AU - Brown, Matthew

AU - Padget, Julian

AU - Coley, David

PY - 2016/12/1

Y1 - 2016/12/1

N2 - There is a growing desire to measure the operational performance of buildings – often many buildings simultaneously – but the cost of sensors and complexity of deployment is a significant constraint. In this paper, we present an approach to minimising the cost of sensing by recognising that researchers are often not interested in the raw data itself but rather some inferred performance metric (e.g. high CO2 levels may indicate poor ventilation). We cast the problem as one of constrained optimisation – specifically, as a bounded knapsack problem (BKP) – to choose the best sensors for the set given each sensor's predictive value and cost. Training data is obtained from a field study comprising a wide range of possible sensors from which a minimum set can be extracted. We validate the method using reliable self-reported event diaries as a measure of actual performance. Results show that the method produces sensors sets that are good predictors of performance and the optimal sets vary substantially with the constraint parameters. Furthermore, valuable yet expensive sensors are often not chosen in the optimal set due to strong co-incidence of sensor signals. For example, light level and sound level often increase at the same time. The overall implication of the work is that a large number of co-incident low-cost sensors can be used to build up a picture of building performance, without significantly compromising information content, and this could have major benefits for the smart metering industry.

AB - There is a growing desire to measure the operational performance of buildings – often many buildings simultaneously – but the cost of sensors and complexity of deployment is a significant constraint. In this paper, we present an approach to minimising the cost of sensing by recognising that researchers are often not interested in the raw data itself but rather some inferred performance metric (e.g. high CO2 levels may indicate poor ventilation). We cast the problem as one of constrained optimisation – specifically, as a bounded knapsack problem (BKP) – to choose the best sensors for the set given each sensor's predictive value and cost. Training data is obtained from a field study comprising a wide range of possible sensors from which a minimum set can be extracted. We validate the method using reliable self-reported event diaries as a measure of actual performance. Results show that the method produces sensors sets that are good predictors of performance and the optimal sets vary substantially with the constraint parameters. Furthermore, valuable yet expensive sensors are often not chosen in the optimal set due to strong co-incidence of sensor signals. For example, light level and sound level often increase at the same time. The overall implication of the work is that a large number of co-incident low-cost sensors can be used to build up a picture of building performance, without significantly compromising information content, and this could have major benefits for the smart metering industry.

UR - http://dx.doi.org/10.1016/j.buildenv.2016.09.004

U2 - 10.1016/j.buildenv.2016.09.004

DO - 10.1016/j.buildenv.2016.09.004

M3 - Article

VL - 110

SP - 11

EP - 22

JO - Building and Environment

T2 - Building and Environment

JF - Building and Environment

SN - 0360-1323

ER -