Statistics of building-specific load forecasting models

Abstract

This paper reviews a method of load forecasting specifically for predicting a building's electrical load for demand resource planning. The authors introduced a general problem formulation for building-specific load forecasting in previous works. This paper will enhance this idea with extensive forecaster performance and results based on studies done using historical building demand and thermal data collected for the main library building at Drexel University. These results demonstrate the improvement obtained by including building-specific parameters in the load forecast. Additionally, the variability of this method and how it can inform demand-side decision making is explored, particularly in allowing the manager of a controllable load to assess his or her risk and capabilities when participating in the energy market.