PNNL

Abstract

Machine learning feature selection was conducted to understand the impact of various weather attributes on residential electricity demand and its components in the northwestern United States. Unique residential load profile data were obtained from the Northwest Energy Efficiency Alliance (NEEA) and processed to yield hourly load profiles with the same temporal resolution and duration as weather condition data from the National Oceanic and Atmospheric Administration (NOAA) at representative weather stations. The data were divided into five seasonal conditions. For each condition and each load component, the influences of weather factors were evaluated and quantified using cross-correlation, principal component analysis, and mutual information evaluation. Then predictive models were developed based on the ranked/screened factors using the regression tree (RT) and random forest (RF) approaches. After multi-fold cross-validation, the optimal complexity/depth of the regress tree models is found to vary for different load components, and the prediction accuracy using RT and weather data can be higher than 80% for heating and refrigeration, but as low as 30% for ventilation and cooking. The RF models can provide more accurate and consistent predictions than RT. The developed models provide guidance on improving load profile generation and can serve as a standalone predictive tool for approximating load profiles within balancing authority regions or climate zones where load profile data are not available.