About BuildingEnergy

BuildingEnergy leverages advanced machine learning techniques to analyze data from the ResStock project, a comprehensive modeling tool developed by the National Renewable Energy Laboratory (NREL). ResStock combines extensive public and private data sources, statistical sampling, detailed subhourly building simulations, and high-performance computing to achieve unprecedented granularity and accuracy in modeling the diversity of the U.S. residential housing stock.

Our analysis combines this powerful machine learning foundation with fundamental engineering formulas and a sophisticated inference engine that synthesizes information from multiple sources. This multi-layered approach allows us to provide precise and insightful analyses of building performance and energy efficiency tailored to your specific location and building characteristics.

The system intelligently integrates:

• Machine learning models trained on ResStock's extensive housing stock database
• Engineering formulas for heating, cooling, and electrical loads
• Smart inference from multiple data sources including weather patterns, utility rates, and building codes
• Location-specific climate data and degree-day calculations