Using a fixed effects model to isolate the effects of dynamic societal conditions, this research examines the drivers of utility burdens in three U.S. cities at a neighborhood scale. Energy burden reduction opportunities are forecasted through an evaluation of potential energy efficiency technologies using several utility cost tests. A discussion around leveraging current and future energy policies to redress systemic inequities in the residential energy ecosystem concludes.

In this study, novel datasets and machine learning
modeling techniques are applied to evaluate the relationship between urban tree canopy, energy burden, redlining, energy use intensities, population migration, socio-economic indicators, and displacement, among others, at the neighborhood level in three U.S. cities.

This study used advanced data analytics to develop three energy-use forecasts for the City of Tampa – Business-as-Usual (BAU), Moderate (MOD),
and Ambitious (AMB) Electricity Scenarios.