Assessment of Occupancy Estimators for Smart Buildings

Claudia Chitu, Grigore Stamatescu, Iulia Stamatescu, Valentin Sgarciu

Research output: Contribution to conferencePaperResearchpeer-review

Abstract

Dense distributed sensor systems deployed to monitor and control the built environment open up wide application areas for improving the quality of life through smart spaces. By implementing these systems in residential or commercial buildings, more efficient, pervasive, real-time and finally more robust decision support is achieved. As one of the key tasks, high accuracy occupancy detection and estimation within buildings offers the potential to improve HVAC utilization while reducing maintenance needs, enhancing energy savings for building operators as well as a more suitable thermal comfort for occupants. In this context the main contribution of the paper consists of an assessment of supervised machine learning techniques namely random forests and extreme machine learning neural networks for indirect occupancy profile estimation. The methods are applied on a benchmarking dataset of indoor carbon dioxide measurements and ventilation damper positions as collected from the building information system. The impact of data preprocessing through filtering and smoothing as well as hardware constraints and cloud distributed processing for algorithm deployment are also discussed. We highlight key challenges and discuss how the learned models can be integrated for online operation to improve energy efficiency.
Original languageEnglish
Number of pages6
Publication statusPublished - 18 Sep 2019
Event10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications - Metz, France
Duration: 18 Sep 201921 Sep 2019

Conference

Conference10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications
Abbreviated titleIDAACS 2019
CountryFrance
CityMetz
Period18/09/1921/09/19

Fingerprint

Intelligent buildings
Learning systems
Thermal comfort
Benchmarking
Ventilation
Energy efficiency
Carbon dioxide
Energy conservation
Information systems
Neural networks
Hardware
Sensors
Processing
HVAC

Cite this

Chitu, C., Stamatescu, G., Stamatescu, I., & Sgarciu, V. (2019). Assessment of Occupancy Estimators for Smart Buildings. Paper presented at 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Metz, France.

Assessment of Occupancy Estimators for Smart Buildings. / Chitu, Claudia; Stamatescu, Grigore; Stamatescu, Iulia; Sgarciu, Valentin.

2019. Paper presented at 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Metz, France.

Research output: Contribution to conferencePaperResearchpeer-review

Chitu, C, Stamatescu, G, Stamatescu, I & Sgarciu, V 2019, 'Assessment of Occupancy Estimators for Smart Buildings' Paper presented at 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Metz, France, 18/09/19 - 21/09/19, .
Chitu C, Stamatescu G, Stamatescu I, Sgarciu V. Assessment of Occupancy Estimators for Smart Buildings. 2019. Paper presented at 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Metz, France.
Chitu, Claudia ; Stamatescu, Grigore ; Stamatescu, Iulia ; Sgarciu, Valentin. / Assessment of Occupancy Estimators for Smart Buildings. Paper presented at 10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, Metz, France.6 p.
@conference{d4f92af17fe6446b8d8b8f67ba005af1,
title = "Assessment of Occupancy Estimators for Smart Buildings",
abstract = "Dense distributed sensor systems deployed to monitor and control the built environment open up wide application areas for improving the quality of life through smart spaces. By implementing these systems in residential or commercial buildings, more efficient, pervasive, real-time and finally more robust decision support is achieved. As one of the key tasks, high accuracy occupancy detection and estimation within buildings offers the potential to improve HVAC utilization while reducing maintenance needs, enhancing energy savings for building operators as well as a more suitable thermal comfort for occupants. In this context the main contribution of the paper consists of an assessment of supervised machine learning techniques namely random forests and extreme machine learning neural networks for indirect occupancy profile estimation. The methods are applied on a benchmarking dataset of indoor carbon dioxide measurements and ventilation damper positions as collected from the building information system. The impact of data preprocessing through filtering and smoothing as well as hardware constraints and cloud distributed processing for algorithm deployment are also discussed. We highlight key challenges and discuss how the learned models can be integrated for online operation to improve energy efficiency.",
author = "Claudia Chitu and Grigore Stamatescu and Iulia Stamatescu and Valentin Sgarciu",
year = "2019",
month = "9",
day = "18",
language = "English",
note = "10th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2019 ; Conference date: 18-09-2019 Through 21-09-2019",

}

TY - CONF

T1 - Assessment of Occupancy Estimators for Smart Buildings

AU - Chitu, Claudia

AU - Stamatescu, Grigore

AU - Stamatescu, Iulia

AU - Sgarciu, Valentin

PY - 2019/9/18

Y1 - 2019/9/18

N2 - Dense distributed sensor systems deployed to monitor and control the built environment open up wide application areas for improving the quality of life through smart spaces. By implementing these systems in residential or commercial buildings, more efficient, pervasive, real-time and finally more robust decision support is achieved. As one of the key tasks, high accuracy occupancy detection and estimation within buildings offers the potential to improve HVAC utilization while reducing maintenance needs, enhancing energy savings for building operators as well as a more suitable thermal comfort for occupants. In this context the main contribution of the paper consists of an assessment of supervised machine learning techniques namely random forests and extreme machine learning neural networks for indirect occupancy profile estimation. The methods are applied on a benchmarking dataset of indoor carbon dioxide measurements and ventilation damper positions as collected from the building information system. The impact of data preprocessing through filtering and smoothing as well as hardware constraints and cloud distributed processing for algorithm deployment are also discussed. We highlight key challenges and discuss how the learned models can be integrated for online operation to improve energy efficiency.

AB - Dense distributed sensor systems deployed to monitor and control the built environment open up wide application areas for improving the quality of life through smart spaces. By implementing these systems in residential or commercial buildings, more efficient, pervasive, real-time and finally more robust decision support is achieved. As one of the key tasks, high accuracy occupancy detection and estimation within buildings offers the potential to improve HVAC utilization while reducing maintenance needs, enhancing energy savings for building operators as well as a more suitable thermal comfort for occupants. In this context the main contribution of the paper consists of an assessment of supervised machine learning techniques namely random forests and extreme machine learning neural networks for indirect occupancy profile estimation. The methods are applied on a benchmarking dataset of indoor carbon dioxide measurements and ventilation damper positions as collected from the building information system. The impact of data preprocessing through filtering and smoothing as well as hardware constraints and cloud distributed processing for algorithm deployment are also discussed. We highlight key challenges and discuss how the learned models can be integrated for online operation to improve energy efficiency.

M3 - Paper

ER -