Energy self-sufficiency and resilience are important elements for long-term urban sustainability. Energy supply in many cities in the United States has been highly dependent on fossil-fuels, partly linked with the high energy–consuming lifestyles of urban residents, both at home and outside (i.e., residential and non-residential energy consumption). In this work, we identify electricity consumption spatial trends and profiles across neighborhoods in the city of Chicago.
Toward this goal, we use an anonymous dataset provided by Commonwealth Edison (ComEd; Chicago’s main electricity provider), which includes electricity consumption data of residential and non-residential accounts in Chicago. We aggregate electricity consumption to the census tract level and merge the data with socio-economic data as well as with the Primary Land Use Tax Lot Output (PLUTO) dataset. Then, we apply machine learning clustering methods to categorize electricity consumption patterns at the census tract level. The output demonstrates how specific profiles of electricity consumption emerge across census tracts, which is the first step to be able to develop tailored policies to lower energy consumption—that is, one single policy does not fit all electricity consumption patterns. Furthermore, we analyze clusters and interpret the impacts of socio-economic and land-use variables on the profiles and patterns identified. The result of this study can help engineers, urban planners, and policy-makers develop actionable strategies for electricity consumption management, with the ultimate goal to better understand how energy is consumed to eventually lower energy consumption.

Keywords
Electricity consumption, Clustering, Machine learning, Urban sustainability,