Home-by-Home Residential Building Energy-Load Profile Optimization for Rapid Decarbonization using Scalable and Personalized Sensor-Independent Efficiency and Emissions Guides for Households

The 93 million US residential households emit between 5-80 tons of CO2-equivalents (CO2e) each year, contributing between 20-40% of US emissions. The US committed to 50% CO2e by 2030 and net-zero CO2e by 2050, but households lack the toolsets to guide efficiency improvements, renewable energy implementation, and electrification strategies specifically for their individual homes. High-efficiency mechanical equipment and renewable energy will account for ~90% of net-zero goals for residential buildings. Most building technologies rely on sensors to generate data and subsidize upgrades. In residential households, reliance on sensors creates high barriers to entry from cost, interoperability complexities, and cybersecurity risks that have slowed the pace of achieving net-zero goals. This Phase I SBIR R&D, led by Universal Schedule and Booking (USB) in partnership with Texas A&M University Mechanical Engineering Lab Subawardee, will demonstrate proof-of-concept for energy-efficiency modeling on home-by-home bases with sensor-independent machine learning. This provides the technical basis to develop data-driven decision-making guides for households to walk consumers through specific upgrades needed to save money, be financially rewarded, and reach our country’s net-zero goals. USB’s proprietary internet-of-things infrastructure technology and validated business model provides households and stakeholders mutually beneficial, scientifically valid, technology-enabled pathways to reach net-zero.