The good, the bad, and the ugly: Data-driven load profile discord identification in a large building portfolio

Project Description:

This project focused on developing a data-driven algorithm for automated load profile discord identification (ALDI) in a large portfolio of buildings. Specifically, ALDI 1) uses the matrix profile (MP) method to quantify the similarities of daily subsequences in time series meter data, 2) compares daily MP values with typical-day MP distributions using Kolmogorov-Smirnov test, and 3) identifies daily load profile discords in a large building portfolio. We demonstrated ALDI using the metering data of both an academic campus, (UT Austin) and a residential neighborhood, (Pecan street).

Project Collaborators:

• Intelligent Environments Laboratory, UT Austin, (http://nagy.caee.utexas.edu)
• Buildings and Thermal Sciences Center, NREL, (https://www.nrel.gov/buildings/index.html)

Citation of the project:

Park, June Young, et al. "The good, the bad, and the ugly: Data-driven load profile discord identification in a large building portfolio." Energy and Buildings 215 (2020): 109892. (https://doi.org/10.1016/j.enbuild.2020.109892)