Characterizing the Key Predictors of Renewable Energy Penetration for Sustainable and Resilient Communities

Abstract

With a mean annual growth rate of roughly 50%, the solar industry has experienced unprecedented growth in the last decade, largely owing to the steadily falling prices of solar installations. Utility-scale energy prices from solar installations are now comparable to all other forms of generation, and the cost of residential system installation has dropped on average by 70%, before incentives. However, the factors explaining this trend extend beyond falling prices. This paper presents a data-centric framework, grounded in machine-learning theory, to estimate solar installations as a function of social, economic, and demographic factors. By doing so, the authors seek to identify the key influencing factors of a community’s adoption of renewable energy. To illustrate the applicability of the proposed data-centric framework, the state of California was selected as a case study. Results indicate that differences in population-adjusted adoption rates can be largely explained by variations in key factors such as income, race, political leaning, average electric power consumption, and solar radiation. By analyzing these differences, decision makers can devise effective incentive mechanisms to nudge homeowners toward improved access to renewable technology.