skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

This content will become publicly available on November 28, 2019

Title: Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification

Abstract

With the rapid advances in sensing and digital technologies, cyber-physical systems are regarded as the most viable platforms for improving building design and management. Researchers investigated the possibility of integrating energy management systems with cyber-physical systems to form energy-cyber-physical systems in order to promote building energy management. However, minimizing energy consumption while fulfilling building functions for energy-cyber-physical systems is challenging due to the dynamics of building occupants. As occupant behavior is a major source of uncertainty for energy management, ignoring it often results in both energy waste caused by overheating and overcooling as well as discomfort due to insufficient thermal and ventilation services. To mitigate such uncertainties, this study proposes an occupancy-linked energy-cyber-physical system that incorporates WiFi probe-based occupancy detection. The proposed framework utilizes ensemble classification algorithms to extract three forms of occupancy information. It creates a data interface to link energy management systems and cyber-physical systems and allows for automated occupancy detection and interpretation by assembling multiple weak classifiers for WiFi signals. A validation experiment in a large office room was conducted to examine the performance of the proposed occupancy-linked energy-cyber-physical systems. The experiment and simulation results suggest that, with a proper classifier and occupancy data type, the proposedmore » model can potentially save about 26.4% of energy consumption in cooling and ventilation demands.« less

Authors:
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [3];  [4]; ORCiD logo [5]
  1. Southeast Univ., Nanjing (China). School of Architecture
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Building Technology and Urban Systems Div.
  3. Tsinghua Univ., Beijing (China). Dept. of Construction Management
  4. Northeastern Univ., Boston, MA (United States). Dept. of Civil and Environment Engineering
  5. City Univ. of Hong Kong (China). Dept. of Architecture and Civil 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), Building Technologies Office (EE-5B)
OSTI Identifier:
1526578
Grant/Contract Number:  
AC02-05CH11231
Resource Type:
Accepted Manuscript
Journal Name:
Applied Energy
Additional Journal Information:
Journal Volume: 236; Journal Issue: C; Journal ID: ISSN 0306-2619
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION; Energy-Cyber-Physical Systems; Building occupancy; Wi-Fi probe technology; ensemble algorithm

Citation Formats

Wang, Wei, Hong, Tianzhen, Li, Nan, Wang, Ryan Qi, and Chen, Jiayu. Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification. United States: N. p., 2018. Web. doi:10.1016/j.apenergy.2018.11.079.
Wang, Wei, Hong, Tianzhen, Li, Nan, Wang, Ryan Qi, & Chen, Jiayu. Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification. United States. doi:10.1016/j.apenergy.2018.11.079.
Wang, Wei, Hong, Tianzhen, Li, Nan, Wang, Ryan Qi, and Chen, Jiayu. Wed . "Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification". United States. doi:10.1016/j.apenergy.2018.11.079.
@article{osti_1526578,
title = {Linking energy-cyber-physical systems with occupancy prediction and interpretation through WiFi probe-based ensemble classification},
author = {Wang, Wei and Hong, Tianzhen and Li, Nan and Wang, Ryan Qi and Chen, Jiayu},
abstractNote = {With the rapid advances in sensing and digital technologies, cyber-physical systems are regarded as the most viable platforms for improving building design and management. Researchers investigated the possibility of integrating energy management systems with cyber-physical systems to form energy-cyber-physical systems in order to promote building energy management. However, minimizing energy consumption while fulfilling building functions for energy-cyber-physical systems is challenging due to the dynamics of building occupants. As occupant behavior is a major source of uncertainty for energy management, ignoring it often results in both energy waste caused by overheating and overcooling as well as discomfort due to insufficient thermal and ventilation services. To mitigate such uncertainties, this study proposes an occupancy-linked energy-cyber-physical system that incorporates WiFi probe-based occupancy detection. The proposed framework utilizes ensemble classification algorithms to extract three forms of occupancy information. It creates a data interface to link energy management systems and cyber-physical systems and allows for automated occupancy detection and interpretation by assembling multiple weak classifiers for WiFi signals. A validation experiment in a large office room was conducted to examine the performance of the proposed occupancy-linked energy-cyber-physical systems. The experiment and simulation results suggest that, with a proper classifier and occupancy data type, the proposed model can potentially save about 26.4% of energy consumption in cooling and ventilation demands.},
doi = {10.1016/j.apenergy.2018.11.079},
journal = {Applied Energy},
number = C,
volume = 236,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
This content will become publicly available on November 28, 2019
Publisher's Version of Record

Citation Metrics:
Cited by: 6 works
Citation information provided by
Web of Science

Save / Share: