Publication
DIET Controller: Dynamic Indoor Environment using Deep Reinforcement Learning
Publications associées (86)
Fusing Pre-existing Knowledge and Machine Learning for Enhanced Building Thermal Modeling and Control
Buildings play a pivotal role in the ongoing worldwide energy transition, accounting for 30% of the global energy consumption. With traditional engineering solutions reaching their limits to tackle such large-scale problems, data-driven methods and Machine ...
EPFL2024Inverse design of metal-organic frameworks for direct air capture of CO2via deep reinforcement learning
Berend Smit, Xiaoqi Zhang, Sauradeep Majumdar, Hyunsoo Park
The combination of several interesting characteristics makes metal-organic frameworks (MOFs) a highly sought-after class of nanomaterials for a broad range of applications like gas storage and separation, catalysis, drug delivery, and so on. However, the e ...
Royal Soc Chemistry2024Building ventilation and outdoor air pollution: Implications for health, comfort and energy
As humans spend most of their time indoors, indoor air quality (IAQ) significantly impacts their health. In parallel, building ventilation consumes significant energy, contributing to climate change. However, the relationships between the building ventilat ...
EPFL2023Transparent structured conductive coating for applications in smart windows.
Solar radiation reaching the surface of the earth for a period of one hour contains more energy than that consumed by mankind over an entire year. Some of this solar energy is already collected by photovoltaic cells to cover the electricity needs of buildi ...
EPFL2023Energy, SBS symptoms, and productivity in Swiss open-space offices: Economic evaluation of standard, actual, and optimum scenarios
Dusan Licina, Dolaana Khovalyg, Verena Marie Barthelmes, Arnab Chatterjee, Cecile Anne Berquand
The fundamental aspiration of new-generation high-performing buildings is to reduce energy use while securing indoor environmental quality conducive to human health and productivity. However, existing frameworks for identifying Key Performance Indicators ( ...
PERGAMON-ELSEVIER SCIENCE LTD2023Dynamic indoor thermal environment using Reinforcement Learning-based controls: Opportunities and challenges
Dolaana Khovalyg, Arnab Chatterjee
Currently, the indoor thermal environment in many buildings is controlled by conventional control techniques that maintain the indoor temperature within a prescribed deadband. The latest research provides evidence that more dynamic variations of the indoor ...
2023Assessment of Monitoring Strategies for Inhalation Exposure and Occupancy in Office Environments
Given people's significant time spent indoors, ensuring good indoor air quality (IAQ) is essential because it significantly influences occupants' health and productivity. Office buildings consume about 50% of commercial building energy and 18% of total bui ...
EPFL2023Preserving suspended structures with light façades (1960-1980).Architectural study and retrofitting proposals
Nowadays, the energy efficiency of the existing building stock is internationally accepted as a topical issue. Energy retrofitting is encouraged, improving the thermal performances of buildings, but often altering the historical image of our cities. Attent ...
EPFL2023Reinforcement learning approach to control an inverted pendulum: A general framework for educational purposes
Machine learning is often cited as a new paradigm in control theory, but is also often viewed as empirical and less intuitive for students than classical model-based methods. This is particularly the case for reinforcement learning, an approach that does n ...
PUBLIC LIBRARY SCIENCE2023PePTM: An Efficient and Accurate Personalized P2P Learning Algorithm for Home Thermal Modeling
Rachid Guerraoui, Alexandre David Olivier Maurer, Omid Ardakanian
Nowadays, the integration of home automation systems with smart thermostats is a common trend, designed to enhance resident comfort and conserve energy. The introduction of smart thermostats that can run machine learning algorithms has opened the door for ...
Basel2023