Regression Models for Demand Reduction based on Cluster Analysis of Load Profiles

TitleRegression Models for Demand Reduction based on Cluster Analysis of Load Profiles
Publication TypeConference Paper
LBNL Report NumberLBNL-2259E
Year of Publication2009
AuthorsYamaguchi, Nobuyuki, Junqiao Han Dudley, Girish Ghatikar, Sila Kiliccote, Mary Ann Piette, and Hiroshi Asano
Secondary AuthorsHan, Junqiao
Conference NameIEEE-PES/IAS Conference on Sustainable Alternative Energy
Conference LocationValencia, Spain
Keywordsautomated demand response, cluster analysis, critical peak pricing, demand reduction, demand response and distributed energy resources center, demand response research center, k-means, regression model, sensitivity to outside air temperature

This paper provides new regression models for demand reduction of Demand Response programs for the purpose of ex ante evaluation of the programs and screening for recruiting customer enrollment into the programs. The proposed regression models employ load sensitivity to outside air temperature and representative load pattern derived from cluster analysis of customer baseline load as explanatoryvariables.The proposed models examined their performances from the viewpoint of validity of explanatory variables and fitness of regressions, using actual load profile data of Pacific Gas and Electric Company’s commercial and industrial customers who participated in the 2008 Critical Peak Pricing program including Manual and Automated Demand Response.

PDF365.98 KB