Building Energy
Building energy research focuses on optimizing energy efficiency and reducing consumption in buildings, primarily through improved control of heating, ventilation, and air conditioning (HVAC) systems. Current research emphasizes data-driven approaches, employing machine learning models like neural networks, reinforcement learning algorithms (including model-predictive control and deep reinforcement learning), and large language models for tasks such as forecasting energy demand, generating control strategies, and automating building management system (BMS) processes. These advancements aim to improve energy efficiency, reduce operational costs, and enhance occupant comfort, contributing significantly to sustainability efforts and the development of smart buildings.
Papers
Machine Learning for Smart and Energy-Efficient Buildings
Hari Prasanna Das, Yu-Wen Lin, Utkarsha Agwan, Lucas Spangher, Alex Devonport, Yu Yang, Jan Drgona, Adrian Chong, Stefano Schiavon, Costas J. Spanos
BEAR: Physics-Principled Building Environment for Control and Reinforcement Learning
Chi Zhang, Yuanyuan Shi, Yize Chen