Skip to main content
Home
  • About Us +

    Researchers in the Building & Industrial Energy Systems Division (BIES) at Lawrence Berkeley National Laboratory work closely with industry, government and key decision makers to inform and develop building and industrial energy systems that increase energy efficiency, save money and improve health and safety for building occupants.

    The BIES Division engages in innovative and creative research to advance energy efficiency in the built environment, one of the world's most critical energy and environmental challenges because buildings are the world's largest energy-users.

    • Access, Directions
    • Division Structure
    • Our Websites
    • Partners
    • Staff
    • Testing Capabilities
    • Art Rosenfeld
    • Join Our Mailing List
    • Resources
  • Research +

    We are at the forefront of cutting-edge research that redefines building technology and explores all areas of urban systems.

    We have been leaders for decades in developing energy-efficient windows, improving indoor air quality, coming up with new ideas to fix the nation's electricity grid, and so much more.

    Visit our research areas at the right to find out more.

    Colum 1 +
    • Windows & Daylighting
    • FLEXLAB® & Systems Integration
    • Electronics, Lighting & Networks
    • Modeling & Simulation
    • Indoor Air Quality
    • High Tech & Industrial
    Colum 2 +
    • Decision Science
    • Energy Analytics
    • The Grid & Demand Response
    • Cool Roofs & Walls
    • Urban Systems
  • Publications
  • News
  • Tools & Guides +

    Explore our tools, guidebooks and software and download for free.

    We offer a variety of technologies designed to simulate and model real-world circumstances to assist in energy-saving programs and help building owners build better buildings. These tools can help calculate performance of building systems like windows and shades, help consumers and builders pick the best windows for a variety of applications and much more.

    • Whole Building
    • Occupant Behavior
    • Lighting
    • Windows and Envelope Materials
    • Cool Surfaces
    • City and Districts

Publications

Publications By Research Area

  • Cool Roofs & Walls
  • Decision Science
  • EMIS
  • Electronics, Lighting & Networks
  • Energy & Financing
  • Energy Analytics
  • FLEXLAB® and Systems Integration
  • High Tech & Industrial
  • Indoor Air Quality
  • Modeling & Simulation
  • The Grid & Demand Response
  • Windows & Daylighting
X Author: Zhe Wang X Term: BTUS Modeling and Simulation

2019

Wang, Zhe, Tianzhen Hong, Mary Ann Piette, and Marco Pritoni."Inferring occupant counts from Wi-Fi data in buildings through machine learning."Building and Environment 158 (2019) 281 - 294. DOI
Wang, Zhe, Tianzhen Hong, and Mary Ann Piette."Predicting plug loads with occupant count data through a deep learning approach."Energy 181 (2019) 29 - 42. DOI
Wang, Zhe, Thomas Parkinson, Peixian Li, Borong Lin, and Tianzhen Hong."The Squeaky wheel: Machine learning for anomaly detection in subjective thermal comfort votes."Building and Environment 151 (2019) 219 - 227. DOI
Wang, Zhe, Tianzhen Hong, and Mary Ann Piette."Data fusion in predicting internal heat gains for office buildings through a deep learning approach."Applied Energy 240 (2019) 386 - 398. DOI
Wang, Zhe, and Tianzhen Hong."Learning occupants’ indoor comfort temperature through a Bayesian inference approach for office buildings in United States."Renewable and Sustainable Energy Reviews (2019) 109593. DOI

Pagination

  • First page « First
  • Previous page ‹ Previous
  • Page 1
  • Page 2

U.S Department of Energy   UC Berkeley

©2025 Energy Technologies Area, Berkeley Lab

OUR ORGANIZATION

  • Lawrence Berkeley National Laboratory
  • Energy Technologies Area
  • Building & Industrial Energy Systems Division
  • Join Our Mailing List
  • Privacy and Security Notice