Date of Award
Master of Science (MS)
College of Science and Mathematics
Thesis Sponsor/Dissertation Chair/Project Chair
Demand response is a valuable tool for improving the reliability, stability, and financial efficiency of smart grids. With the intention of altering customer power consumption patterns, utility companies often implement strategies such as time-of-use (TOU) programs. Although effective in some situations, TOU programs struggle to perform in highly developed countries due to the complexity of human behavior. In this study, we analyze power consumption readings from smart meters from 5567 households in London, UK from November 2011 to February 2014 to measure the success of the TOU program. We additionally consider the variability of weather conditions and customer demographics when determining program outcome. We establish a relationship between time of day and low/high power consumption both in standard (STD) customers and TOU customers. Furthermore, we apply deep learning via a Long short-term memory (LSTM) model and determine predictability based on weather features through drill down operations.
Johnson, Matthew S., "Towards Machine Learning-Based Demand Response Forecasting Using Smart Grid Data" (2021). Theses, Dissertations and Culminating Projects. 772.