Occupancy prediction through Markov based feedback recurrent neural network (M-FRNN) algorithm with WiFi probe technology
Abstract
Accurate occupancy prediction can improve facility control and energy efficiency of buildings. In recent years, buildings’ exiting WiFi infrastructures have been widely studied in the research of occupancy and energy conservation. However, using WiFi to assess occupancy is challenging due to that occupancy information is often characterized stochastically and varies with time and easily disturbed by building components. To overcome such limitations, this study utilizes WiFi probe technology to actively scan WiFi connection requests and responses between access points and network devices of building occupants. With captured signals, this study proposed a Markov based feedback recurrent neural network (M-FRNN) algorithm to model and predict the occupancy profiles. One on-site experiment was conducted to collect ground truth data using camera-based video analysis and the results were used to validate the M-FRNN occupancy prediction model over a 9-day measurement period. From the results, the M-FRNN based occupancy model using WiFi probes shows best accuracies can reach 80.9%, 89.6%, and 93.9% with a tolerance of 2, 3, and 4 occupants respectively. In conclusion, this study demonstrated that WiFi data coupled with stochastic machine learning system can provide a viable alternative to determine a building's occupancy profile.
- Authors:
-
- City Univ. of Hong Kong, Kowloon (Hong Kong). Dept. of Architecture and Civil Engineering; Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Building Technology and Urban Systems Division
- City Univ. of Hong Kong, Kowloon (Hong Kong). Dept. of Architecture and Civil Engineering
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Building Technology and Urban Systems Division
- Huazhong Univ. of Science and Technology, Wuhan, Hubei (China). Dept. of Building Environment and Energy Engineering, School of Environment of Science and Engineering
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
- OSTI Identifier:
- 1506317
- Alternate Identifier(s):
- OSTI ID: 1548443
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Building and Environment
- Additional Journal Information:
- Journal Volume: 138; Journal Issue: C; Journal ID: ISSN 0360-1323
- Publisher:
- Elsevier
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Citation Formats
Wang, Wei, Chen, Jiayu, Hong, Tianzhen, and Zhu, Na. Occupancy prediction through Markov based feedback recurrent neural network (M-FRNN) algorithm with WiFi probe technology. United States: N. p., 2018.
Web. doi:10.1016/j.buildenv.2018.04.034.
Wang, Wei, Chen, Jiayu, Hong, Tianzhen, & Zhu, Na. Occupancy prediction through Markov based feedback recurrent neural network (M-FRNN) algorithm with WiFi probe technology. United States. https://doi.org/10.1016/j.buildenv.2018.04.034
Wang, Wei, Chen, Jiayu, Hong, Tianzhen, and Zhu, Na. Sat .
"Occupancy prediction through Markov based feedback recurrent neural network (M-FRNN) algorithm with WiFi probe technology". United States. https://doi.org/10.1016/j.buildenv.2018.04.034. https://www.osti.gov/servlets/purl/1506317.
@article{osti_1506317,
title = {Occupancy prediction through Markov based feedback recurrent neural network (M-FRNN) algorithm with WiFi probe technology},
author = {Wang, Wei and Chen, Jiayu and Hong, Tianzhen and Zhu, Na},
abstractNote = {Accurate occupancy prediction can improve facility control and energy efficiency of buildings. In recent years, buildings’ exiting WiFi infrastructures have been widely studied in the research of occupancy and energy conservation. However, using WiFi to assess occupancy is challenging due to that occupancy information is often characterized stochastically and varies with time and easily disturbed by building components. To overcome such limitations, this study utilizes WiFi probe technology to actively scan WiFi connection requests and responses between access points and network devices of building occupants. With captured signals, this study proposed a Markov based feedback recurrent neural network (M-FRNN) algorithm to model and predict the occupancy profiles. One on-site experiment was conducted to collect ground truth data using camera-based video analysis and the results were used to validate the M-FRNN occupancy prediction model over a 9-day measurement period. From the results, the M-FRNN based occupancy model using WiFi probes shows best accuracies can reach 80.9%, 89.6%, and 93.9% with a tolerance of 2, 3, and 4 occupants respectively. In conclusion, this study demonstrated that WiFi data coupled with stochastic machine learning system can provide a viable alternative to determine a building's occupancy profile.},
doi = {10.1016/j.buildenv.2018.04.034},
journal = {Building and Environment},
number = C,
volume = 138,
place = {United States},
year = {Sat Apr 28 00:00:00 EDT 2018},
month = {Sat Apr 28 00:00:00 EDT 2018}
}
Web of Science
Works referenced in this record:
Demand response and smart grids—A survey
journal, February 2014
- Siano, Pierluigi
- Renewable and Sustainable Energy Reviews, Vol. 30
Demand side management: Benefits and challenges
journal, December 2008
- Strbac, Goran
- Energy Policy, Vol. 36, Issue 12
Why is the reliability of building simulation limited as a tool for evaluating energy conservation measures?
journal, December 2015
- Li, Nan; Yang, Zheng; Becerik-Gerber, Burcin
- Applied Energy, Vol. 159
A review on simulation-based optimization methods applied to building performance analysis
journal, January 2014
- Nguyen, Anh-Tuan; Reiter, Sigrid; Rigo, Philippe
- Applied Energy, Vol. 113
Energy performance building evaluation in Mediterranean countries: Comparison between software simulations and operating rating simulation
journal, January 2008
- Tronchin, Lamberto; Fabbri, Kristian
- Energy and Buildings, Vol. 40, Issue 7
Making the ‘rebound effect’ more useful for performance evaluation of thermal retrofits of existing homes: Defining the ‘energy savings deficit’ and the ‘energy performance gap’
journal, February 2014
- Galvin, Ray
- Energy and Buildings, Vol. 69
The gap between predicted and measured energy performance of buildings: A framework for investigation
journal, May 2014
- de Wilde, Pieter
- Automation in Construction, Vol. 41
Predicted vs. actual energy performance of non-domestic buildings: Using post-occupancy evaluation data to reduce the performance gap
journal, September 2012
- Menezes, Anna Carolina; Cripps, Andrew; Bouchlaghem, Dino
- Applied Energy, Vol. 97
Ten questions concerning occupant behavior in buildings: The big picture
journal, March 2017
- Hong, Tianzhen; Yan, Da; D'Oca, Simona
- Building and Environment, Vol. 114
Importance of occupancy information for building climate control
journal, January 2013
- Oldewurtel, Frauke; Sturzenegger, David; Morari, Manfred
- Applied Energy, Vol. 101
Experimental assessment of room occupancy patterns in an office building. Comparison of different approaches based on CO 2 concentrations and computer power consumption
journal, August 2017
- Díaz, J. A.; Jiménez, M. J.
- Applied Energy, Vol. 199
The dark side of occupants’ behaviour on building energy use
journal, February 2010
- Masoso, O. T.; Grobler, L. J.
- Energy and Buildings, Vol. 42, Issue 2
Dynamic energy-consumption indicators for domestic appliances: environment, behaviour and design
journal, September 2003
- Wood, G.; Newborough, M.
- Energy and Buildings, Vol. 35, Issue 8
IEA EBC Annex 66: Definition and simulation of occupant behavior in buildings
journal, December 2017
- Yan, Da; Hong, Tianzhen; Dong, Bing
- Energy and Buildings, Vol. 156
Improving the accuracy of energy baseline models for commercial buildings with occupancy data
journal, October 2016
- Liang, Xin; Hong, Tianzhen; Shen, Geoffrey Qiping
- Applied Energy, Vol. 179
Energy conservation through flexible HVAC management in large spaces: An IPS-based demand-driven control (IDC) system
journal, November 2017
- Wang, Wei; Chen, Jiayu; Lu, Yujie
- Automation in Construction, Vol. 83
Occupancy-based zone-climate control for energy-efficient buildings: Complexity vs. performance
journal, June 2013
- Goyal, Siddharth; Ingley, Herbert A.; Barooah, Prabir
- Applied Energy, Vol. 106
Occupancy-based demand response and thermal comfort optimization in microgrids with renewable energy sources and energy storage
journal, February 2016
- Korkas, Christos D.; Baldi, Simone; Michailidis, Iakovos
- Applied Energy, Vol. 163
Modeling and predicting occupancy profile in office space with a Wi-Fi probe-based Dynamic Markov Time-Window Inference approach
journal, November 2017
- Wang, Wei; Chen, Jiayu; Song, Xinyi
- Building and Environment, Vol. 124
Advances in research and applications of energy-related occupant behavior in buildings
journal, March 2016
- Hong, Tianzhen; Taylor-Lange, Sarah C.; D’Oca, Simona
- Energy and Buildings, Vol. 116
Occupant behavior modeling for building performance simulation: Current state and future challenges
journal, November 2015
- Yan, Da; O’Brien, William; Hong, Tianzhen
- Energy and Buildings, Vol. 107
Building energy model calibration with schedules derived from electricity use data
journal, March 2017
- Kim, Yang-Seon; Heidarinejad, Mohammad; Dahlhausen, Matthew
- Applied Energy, Vol. 190
Occupancy learning-based demand-driven cooling control for office spaces
journal, September 2017
- Peng, Yuzhen; Rysanek, Adam; Nagy, Zoltán
- Building and Environment, Vol. 122
Simulation and visualization of energy-related occupant behavior in office buildings
journal, March 2017
- Chen, Yixing; Liang, Xin; Hong, Tianzhen
- Building Simulation, Vol. 10, Issue 6
Block Configuration Modeling: A novel simulation model to emulate building occupant peer networks and their impact on building energy consumption
journal, May 2013
- Chen, Jiayu; Jain, Rishee K.; Taylor, John E.
- Applied Energy, Vol. 105
A behavior-based decision-making model for energy performance contracting in building retrofit
journal, December 2017
- Lu, Yujie; Zhang, Nan; Chen, Jiayu
- Energy and Buildings, Vol. 156
Human-based energy retrofits in residential buildings: A cost-effective alternative to traditional physical strategies
journal, November 2014
- Pisello, Anna Laura; Asdrubali, Francesco
- Applied Energy, Vol. 133
How peers’ personal attitudes affect indoor microclimate and energy need in an institutional building: Results from a continuous monitoring campaign in summer and winter conditions
journal, August 2016
- Pisello, Anna Laura; Castaldo, Veronica Lucia; Piselli, Cristina
- Energy and Buildings, Vol. 126
The role of building occupants' education in their resilience to climate-change related events
journal, November 2017
- Pisello, A. L.; Rosso, F.; Castaldo, V. L.
- Energy and Buildings, Vol. 154
A critical review of observation studies, modeling, and simulation of adaptive occupant behaviors in offices
journal, December 2013
- Gunay, H. Burak; O'Brien, William; Beausoleil-Morrison, Ian
- Building and Environment, Vol. 70
Towards a sensor for detecting human presence and characterizing activity
journal, February 2011
- Benezeth, Y.; Laurent, H.; Emile, B.
- Energy and Buildings, Vol. 43, Issue 2-3
Occupancy diversity factors for common university building types
journal, September 2010
- Davis, James A.; Nutter, Darin W.
- Energy and Buildings, Vol. 42, Issue 9
Short term predictions of occupancy in commercial buildings—Performance analysis for stochastic models and machine learning approaches
journal, January 2018
- Li, Zhaoxuan; Dong, Bing
- Energy and Buildings, Vol. 158
Occupancy detection in the office by analyzing surveillance videos and its application to building energy conservation
journal, October 2017
- Zou, Jianhong; Zhao, Qianchuan; Yang, Wen
- Energy and Buildings, Vol. 152
Predictability of occupant presence and performance gap in building energy simulation
journal, December 2017
- Ahn, Ki-Uhn; Kim, Deuk-Woo; Park, Cheol-Soo
- Applied Energy, Vol. 208
CO2-Based Occupancy Detection for On-Line Outdoor Air Flow Control
journal, January 1998
- Wang, Shengwei; Jin, Xinqiao
- Indoor and Built Environment, Vol. 7, Issue 3
Indoor occupancy estimation from carbon dioxide concentration
journal, November 2016
- Jiang, Chaoyang; Masood, Mustafa K.; Soh, Yeng Chai
- Energy and Buildings, Vol. 131
Experimental Validation of CO2-Based Occupancy Detection for Demand-Controlled Ventilation
journal, November 1999
- Wang, Shengwei; Burnett, John; Chong, Hoishing
- Indoor and Built Environment, Vol. 8, Issue 6
Development and In-situ validation of a multi-zone demand-controlled ventilation strategy using a limited number of sensors
journal, November 2012
- Shan, Kui; Sun, Yongjun; Wang, Shengwei
- Building and Environment, Vol. 57
Modeling personalized occupancy profiles for representing long term patterns by using ambient context
journal, August 2014
- Yang, Zheng; Becerik-Gerber, Burcin
- Building and Environment, Vol. 78
Review of occupancy sensing systems and occupancy modeling methodologies for the application in institutional buildings
journal, June 2016
- Yang, Junjing; Santamouris, Mattheos; Lee, Siew Eang
- Energy and Buildings, Vol. 121
Measuring and monitoring occupancy with an RFID based system for demand-driven HVAC operations
journal, July 2012
- Li, Nan; Calis, Gulben; Becerik-Gerber, Burcin
- Automation in Construction, Vol. 24
Understanding occupancy pattern and improving building energy efficiency through Wi-Fi based indoor positioning
journal, March 2017
- Wang, Y.; Shao, L.
- Building and Environment, Vol. 114
Smart probabilistic fingerprinting for WiFi-based indoor positioning with mobile devices
journal, September 2016
- Bisio, Igor; Lavagetto, Fabio; Marchese, Mario
- Pervasive and Mobile Computing, Vol. 31
Wi-Fi multi-floor indoor positioning considering architectural aspects and controlled computational complexity
journal, October 2014
- Campos, Rafael Saraiva; Lovisolo, Lisandro; de Campos, Marcello Luiz R.
- Expert Systems with Applications, Vol. 41, Issue 14
Assessing occupants’ energy load variation through existing wireless network infrastructure in commercial and educational buildings
journal, October 2014
- Chen, Jiayu; Ahn, Changbum
- Energy and Buildings, Vol. 82
Virtual occupancy sensors for real-time occupancy information in buildings
journal, November 2015
- Zhao, Yang; Zeiler, Wim; Boxem, Gert
- Building and Environment, Vol. 93
Building occupancy detection through sensor belief networks
journal, September 2006
- Dodier, Robert H.; Henze, Gregor P.; Tiller, Dale K.
- Energy and Buildings, Vol. 38, Issue 9, p. 1033-1043
Modeling regular occupancy in commercial buildings using stochastic models
journal, September 2015
- Chen, Zhenghua; Xu, Jinming; Soh, Yeng Chai
- Energy and Buildings, Vol. 103
Predicting occupancy counts using physical and statistical Co2-based modeling methodologies
journal, October 2017
- Zuraimi, M. S.; Pantazaras, A.; Chaturvedi, K. A.
- Building and Environment, Vol. 123
Works referencing / citing this record:
Development of a Consecutive Occupancy Estimation Framework for Improving the Energy Demand Prediction Performance of Building Energy Modeling Tools
journal, January 2019
- Kim, Seokho; Sung, Yujin; Sung, Yoondong
- Energies, Vol. 12, Issue 3