• GitHub
  • Home
  • People
  • Research
  • Publications
  • Courses
  • News
  • Contact
  • Internal
UT Shield

Intelligent Environments Laboratory

The University of Texas at Austin
  • Home
  • People
    • Prof. Zoltan Nagy, PhD
    • June Young Park
    • José Ramón Vázquez-Canteli
    • Megan K. McHugh, MSE
    • Ayşegül Demir Dilsiz
    • Hagen Fritz
  • Research
  • Publications
  • GitHub
  • Courses
  • News
  • Contact

January 30, 2019, Filed Under: Publication

Temperature-preference learning with neural networks for occupant-centric building indoor climate controls

Our paper led by Yuzhen Peng from ETH Zurich has been recently published in Building & Environment. We propose an intelligent building control strategy with machine learning techniques together with its design process for creating occupant-centric indoor climate. We demonstrate 4%–25% energy saving potential and the temperature comfort improvement through a real-world experiment.

Y. Peng, Z. Nagy, A. Schlüter, Temperature-preference learning with neural networks for occupant-centric building indoor climate controls, Building and Environment, 2019,

DOI: https://doi.org/10.1016/j.buildenv.2019.01.036

Abstract
Heating, ventilation, and air-conditioning (HVAC) are vital components in providing a comfortable indoor climate for the occupants of buildings. In commercial buildings, HVAC setpoints are set according to average comfort temperatures. However, individual temperature preferences may be different. The purpose of this study is to explore the means of making HVAC systems respond automatically to local occupant temperature preferences. To create an occupant-centric indoor temperature environment, we propose an online-learning-based control strategy together with its design process. Four essential variables from four domains—time, indoor and outdoor climates, and occupant behavior—are extracted to construct datasets for preference models. A neural network algorithm and corresponding hyperparameters are suggested to model temperature preferences. According to time-dependent setpoints learned from dynamic contexts, a set of specified rules is used to determine setpoints for HVAC systems. For a period of five months, the resulting learning-based temperature preference control (LTPC) was applied to a cooling system of an office space under real-world conditions. The four case study rooms consisted of typical office uses: single-person and multi-person offices. The experimental results indicate that occupant preferences in the individual rooms differ from each other in both time horizon and temperature levels. The results report energy savings of between 4% and 25% as compared to static temperature setpoints at the low values of preferred temperature ranges. Meanwhile, during LPTC, the need for occupant interventions for adjusting room temperatures to fit their preferences was reduced from four to nine weekdays a month to a maximum of one weekday a month.

 

Research Highlight

Thermal Comfort & Smart Buildings

This is an excerpt from our review paper Comprehensive analysis of the relationship between thermal comfort and building control research - A Read more 

About Us

The Intelligent Environments Laboratory (IEL), led by Prof. Zoltán Nagy, is an interdisciplinary research group within the Building Energy & Environments (BEE) and Sustainable Systems (SuS) Programs of the Department of Civil, Architectural and Environmental Engineering (CAEE) in the Cockrell School of Engineering of the University of Texas at Austin.

The aim of our research is to rethink the built environment and define Smart Buildings and Cities as spaces that adapt to their occupants and reduce their energy consumption.

We combine data science with building science and apply machine learning to the building and urban scale

Take a look at our projects !

Tags

air handling unit Annex 79 architecture artificial neural network Bluetooth city learn Community engaged research earthquakes environmental monitoring fault detection and diagnostics HVAC integrated design intelligent energy management Lighting Control machine learning Megan McHugh multi-agent systems Occupancy Occupant Centered Control Reinforcement Learning Review Smart Building smart city teaching Thermal Comfort
Tweets by Z0ltanNagy

Research

  • All Projects

UT Energy App – Privacy Policy

Fault detection and diagnostics of air handling units using machine learning and expert rule-sets

Reinforcement Learning in the Built Environment

Reinforcement learning for urban energy systems & demand response

Multi-Agent Reinforcement Learning for demand response & building coordination

IEA-EBC Annex 79: Occupant Centric Design and Operation of Buildings

People

  • Prof. Zoltan Nagy, PhD
  • June Young Park
  • José Ramón Vázquez-Canteli
  • Megan K. McHugh, MSE

Tags

air handling unit Annex 79 architecture artificial neural network Bluetooth city learn Community engaged research earthquakes environmental monitoring fault detection and diagnostics HVAC integrated design intelligent energy management Lighting Control machine learning Megan McHugh multi-agent systems Occupancy Occupant Centered Control Reinforcement Learning Review Smart Building smart city teaching Thermal Comfort
ITS

301 E Dean Keeton St
Austin, TX 78712
512-555-5555
nagy@utexas.edu

UT Home | Emergency Information | Site Policies | Web Accessibility | Web Privacy | Adobe Reader

© The University of Texas at Austin 2021

  • All Projects