%0 Journal Article
%A Jessica Granderson
%A Samuel Fernandes
%A Eliot Crowe
%A Mrinalini Sharma
%A David A Jump
%A Devan Johnson
%B Energy and Buildings
%D 2023
%G eng
%R https://doi.org/10.1016/j.enbuild.2023.113297
%T Accuracy of hourly energy predictions for demand flexibility applications
%V Vol.295 No..113297
%8 06/2023
%X <p>Decarbonization goals in the United States electricity sector are increasing the levels of renewable energy generation<br />in the electricity supply system, and are driving increased attention to building electrification, which will increase<br />the magnitude and shift the timing of the electricity system peak. These changes are motivating new approaches to<br />coordinate building electricity demand with low-carbon renewable generation, elevating the importance of demand<br />flexibility (DF) in buildings and the need to quantify the temporal impacts of DF. In this paper, we first characterize<br />the hourly predictive accuracy of six commonly used baseline models in an application context of quantifying<br />building-level load shift. Our analysis revealed insights such as hours of the day (afternoons), periods of the week<br />(weekends), and seasons (summer) that were predicted with more accuracy than other time periods. In addition, the<br />analysis showed tendencies toward overprediction or underprediction of load. Secondly, we provide the first<br />published investigation of baseline erosion from repeated dispatch of building load shifting. We observed that as the<br />baseline period is pushed back further from the prediction day, the distribution of errors across baseline model<br />predictions increases, with notable inflection points near the three-week erosion point for two of the three models.</p>