• 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

Research

“Research is what I’m doing when I don’t know what I’m doing.
– Wernher von Braun

Research in the Intelligent Environments Laboratory focuses on approaches that allow for resilience and adaptation in the operational phase of buildings. We integrate

  • Data analytics, machine learning and artificial intelligence
  • Occupant comfort and behavior
  • Architectural design and control systems
  • Renewable energy systems and environmental monitoring

and innovate at the intersection of these areas.

We are reinventing the built environment such that it adapts to the occupants and varying internal and external influences.

About 40% of global energy demand and a similar fraction of anthropogenic greenhouse gas (GHG) emissions can be contributed to the built environment. At the same time, buildings have a 50-90% emission reduction potential using existing technologies and their widespread implementation, and should, therefore, be at the center of our focus to address climate change.

Since operational energy dominates the life-cycle energy use of a building, with about 70% share, research at IEL focuses on the operational energy of buildings, and aims at developing control systems that optimize energy use in operation across the building stock. Challenges that need to be overcome are

Challenge 1: Intelligent energy management solutions need to address the fact that the building stock is extremely heterogeneous, and, thus, solutions are needed that can adapt to both this heterogeneity as well as changes throughout the lifespan of buildings. For example, distributed energy generation, such as photovoltaics (PV), combined with electrical storage offers the potential to reduce the load on the electrical grid, and contribute to removing polluting power plants. However, such integration has to be carefully managed to avoid black outs and maintain service in all areas.

Challenge 2: Because up to 30% of the energy use in a building can be directly attributed to occupants, we need to incorporate their behavior and preferences directly and non-intrusively into the operation of buildings. Humans however, are notoriously unpredictable, so modeling and prediction of individuals is challenging. Interestingly, focusing on occupants and providing healthy and comfortable environments in homes and offices, could be also the path to energy efficient buildings.

Both challenges have in common that they require adaptation to individual entities, i.e., a self-tuning feature. In addition, both need simple-to-implement systems that can be scaled across large populations. Therefore, IEL researches adaptive and scalable algorithms, that can be applied to both. One such method is Reinforcement Learning, which is particularly suitable to develop Intelligent Environments.

Current Projects

UT Energy App – Privacy Policy

  The Intelligent Environments Laboratory is releasing the first version of the UT Energy App. This app is intended to provide a way to collect information on climate/temperature and consequent comfort levels for students in UT classrooms and other campus buildings. This data will be used directly by the UT Energy Department to provide students with a better classroom experience and cut costs on climate control.   Key Security Read more 

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

To reduce HVAC energy inefficiencies, fault detection and diagnostics (FDD) has become a growing field of interest. In particular, air handling units (AHU), devices that circulate air and regulate room temperature and humidity, are the primary focus of most HVAC FDD systems. A data-driven FDD for AHUs on a university campus would fill a role in the reduction HVAC energy consumption, which remains one of the main drivers in total building energy Read more 

Reinforcement Learning in the Built Environment

We develop reinforcement learning techniques for energy efficient operation of buildings and systems without the need for mathematical models. Despite the many advantages of RL for application in the built environment, many challenges remain, and are explored in our research. (1) As RL is a relatively new and emerging field, there are no off-the shelf implementations available that researchers could experiment with, in contrast to supervised Read more 

Reinforcement learning for urban energy systems & demand response

Demand response, or demand-side management, improves grid stability by increasing demand flexibility, and shifts peak demand towards periods of peak renewable energy generation by providing consumers with economic incentives. Reinforcement learning has been utilized to control diverse energy systems such as electric vehicles, HVAC systems, smart appliances, or batteries. The future of demand response greatly depends on its ability to prevent Read more 

Multi-Agent Reinforcement Learning for demand response & building coordination

We have introduced a new simulation environment that is the result of merging CitySim, a building energy simulator, and TensorFlow, a powerful machine learning library for deep learning. This new simulation environment has the potential for developing building energy scenarios in which machine learning algorithms, such as deep reinforcement learning, are applied to of the major problems and opportunities modern cities face, e.g., the increased Read more 

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

A new IEA EBC Annex on occupant-centric design and controls has been approved. The Annex will involve about 100 experts from 20 countries for five years and focus on fundamental research issues regarding occupant comfort and behaviour, application to design and operations practice, new technology and tool development, and case studies. The project will be led by Liam O’Brien of Carleton University (Canada) and Prof. Andreas Wagner of Karlsruhe Read more 

Occupant centered building control

The energy savings of buildings promised by automatic control systems are often ineffective due to occupants who may not use the features of the system to the full potential at best, or deactivate the system at worst. Therefore, systems that adapt to the occupant over time without compromising his/her comfort are needed. This occupant centered control (OCC) framework is illustrated in the above Figure. OCC is based on the fact that the data Read more 

Occupancy detection using Bluetooth

  Gathering occupancy data is considered as one of the grand challenges in building information modeling. Direct occupancy detection methods, such as the typical passive infrared (PIR) motion detectors detect motion rather than presence and are difficult to retrofit into existing buildings. In-direct methods, e.g., measuring CO2 levels as a proxy for occupant presence require calibration and training data to perform effectively. In our Read more 

Whole Communities—Whole Health

CHANGING THE WAY SCIENCE HELPS SOCIETY THRIVE IS OUR GRAND CHALLENGE Traditional research studies take “snapshots” of people’s lives at different points in time. Those snapshots give us information, but it’s incomplete. That means we might make incorrect assumptions or develop policies and interventions that are not helpful. But through a combination of biological tracking, environmental sensors, and behavioral monitoring, we will have a more Read more 

Austin building stock under climate change

This project is in collaboration with the Sustainable Built Environment group in the School of Architecture. Each year the city of Austin stays amongst the top of the list of fastest growing metro areas in the country, with an average increase of 160 residents per day. As a result, the building stock in the city is being renovated or torn down and rebuilt at an extremely aggressive pace in an attempt to keep up with the changing city and its Read more 

All Projects

Past Projects (2011—2016) Architecture & Building Systems, ETH Zurich

Wireless Sensor Networks for Building Retrofit

Retrofit measures are an effective means to improve both the heating energy and carbon footprint of a building. On one hand, reducing the losses through the envelope reduces the energy consumption. On the other hand, updating the heating from a fossil-fuel based system to an emission-free one bears the potential… read more 

Occupant Centered Lighting Control

The energy savings of buildings promised by automatic control systems are often ineffective due to occupants who may not use the features of the system to the full potential at best, or deactivate the system at worst. Therefore, systems that adapt to the occupant over time without compromising his/her comfort… read more 

Adaptive Solar Facade

The building facade greatly impacts how much heat has to be added or removed in order to retain a comfortable indoor climate. Given that these processes vary throughout the year, the A/S Research Team has developed an adaptive solar facade. The project combines recent developments in architecture, energy technology and… read more 

Past Projects (2006—2011) Microrobotics, ETH Zurich

Non-Smooth Dynamics Modeling of Wireless Resonant Magnetic Microactuators

In this project, we considered the world’s first really untethered microrobots that are driven by oscillating magnetic fields. The oscillations are converted into mechanical energy and rectified using a spring-mass impact system with friction, leading to stick-slip motion. I model this system using non-smooth multi-body dynamics and can explain several unintuitive… read more 

Intraocular Microrobots and Control Using Field Gradients

This project aimed at developing magnetic microrobotics for ophtalmic surgery. I was involved in developing the magnetic model for assembled-MEMS microrobots. The model is validated through FEM simulations and experiments, and captures the characteristics of complex 3-D structures. It allows us, for the first time, to consider full 6-DOF control of… read more 

Assembling Reconfigurable Endoluminal Surgical (ARES) System

We were developing a modular robotic system that can be swallowed and will assemble inside the G.I. Tract for therapeutic and diagnostic procedures. ETH Zürich is one of four European universities participating in this project, led by Paolo Dario at Scuola Superiore Sant’Anna. My research involved the investigation of the self-assembly… read more 

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