Files in this item



application/pdfSP20-ECE499-Thesis-Wackerman, Grace.pdf (11MB)
(no description provided)PDF


Title:Using socioeconomic data to predict multi-family residential electricity consumption
Author(s):Wackerman, Grace
Contributor(s):Stillwell, Ashlynn
Subject(s):smart meters
electricity usage
multi-family housing
electricity consumption
Abstract:Electricity supply responds to changes in demand, and changing populations alter energy demands for an area. This project characterizes how different population compositions affect electricity consumption using Commonwealth Edison (ComEd) anonymized meter-level data, which show the electricity usage at 30-minute intervals in 2016 for the whole service area, sorted by zip code. The following tasks were completed: -- Compare multi-family residences with different population densities and median incomes in Chicago. -- Characterize different electricity profiles for different zip codes using mean electricity usage for an average day in each month for each zip code. -- Predict multi-family electricity consumption as a function of zip-code-level socioeconomic predictor variables using linear regression. This analysis shows that median age of home, mean commute time, percent of multi-family housing units, median age of population, and percent female are statistically significant predictors of multi-family residential electricity consumption. Daily and monthly electricity profiles also vary notably across zip codes in Chicago. These results can inform electricity providers regarding how forecasted changes in population will likely affect the electricity demand of a particular area.
Issue Date:2020-05
Date Available in IDEALS:2020-06-11

This item appears in the following Collection(s)

Item Statistics