Home-by-Home Residential Building Energy-Load Profile Optimizations

Americans face rising energy costs that could increase 2-3 times by 2050 due to surging energy demands from artificial intelligence and electrification, with families bearing the financial burden unless market forces drive down prices through energy-efficient equipment and incentives. Widespread installation of sensors to monitor and control energy use has been considered a likely pathway to optimize load profiles in homes and for utilities. However, costs of sensors and technical skillsets to use them have limited their installation in homes. Universal Schedule and Booking's (USB) proposed smart digital infrastructure will estimate energy consumption in American homes without auxiliary hardware sensors. This Phase II SBIR R&D will produce prototype machine learning home efficiency guides that: i) high high-accuracy data-driven guides on home-by-home bases to stepwise walk households through energy efficiency upgrades for HVAC equipment and/or appliances and ii) produce market-driven incentives and financial resources within personalization frameworks to assist homeowners with affording the efficiency upgrades. Thus, USB guides will accelerate the adoption of new technologies that are more efficient, from equipment to materials, enabling a faster transformation of the US residential building inventory as high efficiency and a more resilient grid that benefits US manufacturers, finance industry, governments, and nonprofit organizations.