Physics-informed machine learning for building performance simulation-A review of a nascent field

• Apply Physics-Informed Machine Learning (PIML) to advance Building Performance Simulation (BPS). • Conduct an in-depth review of PIML methods and application areas in BPS. • Provide foundation and resources to inform future research of PIML in BPS. • Develop a general guideline for selecting suitable PIML models. • Identify key challenges and future directions for PIML in BPS. Building performance simulation (BPS) is critical for understanding building dynamics and behavior, analyzing the performance of the built environment, optimizing energy efficiency, improving demand flexibility, and enhancing building resilience. However, conducting BPS is not trivial. Traditional BPS relies on accurate building energy…

• NS
  National Science Foundation
• UD
  U.S. Department of Energy

  Awards: DE-AC05-76RL0-1830, DE-AC02-05CH11231
• B
  Battelle
• JH
  Johns Hopkins University
• DF
  Directorate for Engineering

  Award: 1949372
• OO
  Office of Energy Efficiency and Renewable Energy
• BT
  Building Technologies Office