Retrofitting existing buildings presents a powerful opportunity to reduce energy waste from inefficient systems, extend building life, and improve occupant satisfaction. Industry analyses, such as those from McGraw Hill (Bernstein, 2011), consistently show that energy retrofits are one of the most effective strategies for building owners to enhance tenant satisfaction while achieving long-term savings. However, energy efficiency retrofits remain limited. A key barrier is the uncertainty surrounding their financial impacts—particularly how retrofit costs and associated savings might affect both building owners and tenants.

We present in this paper, a proof-of-concept for a data-driven AI/ML-based solution designed to estimate the impact of energy efficiency retrofits on building owners and tenant rents in existing multi-family buildings.

As global temperatures continue to rise, understanding the disconnect between indoor and outdoor thermal conditions has become increasingly important for public health research. Most epidemiological studies linking heat exposure to mortality or morbidity rely on outdoor temperature metrics, which may inadequately represent the indoor environments where people spend most of their time. This study presents a physics-based simulation framework for estimating indoor exposure to dry-bulb temperature, wet-bulb temperature, and absolute humidity. Using Department of Energy (DoE) and National Renewable Energy Laboratory (NREL) residential building prototypes, we modeled summertime indoor thermal conditions across multiple U.S. climate zones. The simulations incorporate diverse factors, including outdoor temperature and humidity variations, extreme heat episodes, and building characteristics such as insulation, roof type, and surface area, as well as varying air-conditioning (AC) operation levels (100%, 50%, and 0%). Preliminary results from hot-humid, hot-dry, and mixed-humid climates reveal that while indoor and outdoor temperature trends are correlated, indoor values remain distinct due to the moderating effects of building envelopes and HVAC operation. Although mechanical cooling and ventilation mitigate indoor heat exposure, their effectiveness diminishes during extreme heat events. Both outdoor weather patterns and AC usage play critical roles in shaping indoor thermal conditions, with peak indoor heat and humidity occurring during July heatwaves. The proposed modeling approach provides a scalable pathway for integrating indoor environmental metrics into population-level epidemiological analyses, thereby improving the precision of heat-related health risk assessments across diverse geographic and climatic contexts.

Resilience hubs serve communities when electricity, water, and food run out during disasters. They double as community centers during other times. Plans for large resilience hubs can be hard to implement and fund though. This study introduces a workflow that can overcome this with a scalable process that uses modular buildings and scalable nanogrids. Scalable, Modular Resilience Hub (SMRH) design process centers around community priorities and needs. The approach combines climate reanlaysis, weather data, agent-based simulation, building energy modeling, and electric power systems analysis to quantify metrics for cost, water availability, electric availability, thermal comfort, and air quality. A case study for the Kahikinui community in Hawaii demonstrates the application of this workflow, where community members helped plan activities and appliance usage which generate load profiles for power system analysis. The results show tradeoffs between capital costs, maintenance costs, thermal comfort, water generation, and electric availability, allowing the community to down-select configurations that meet their needs. The study highlights the importance of considering community priorities and needs in the design of scalable modular resilience hubs and provides a framework for evaluating the performance of these systems.

Buildings typically retain structural integrity during extreme winds, but their envelopes are more vulnerable to damage. This damage exacerbates energy efficiency for buildings in wind-prone areas. To address challenges, this study developed a probabilistic framework that integrates wind hazard assessment with building energy simulation. A case study was conducted on a typical 12-story large office under an extreme wind event in Miami. The building’s energy performance was compared to the expected energy performance of a damaged building envelope, revealing an increase of 23% in energy consumption. The framework provides a solid foundation for architects and engineers with tools for making risk-informed decisions.