PNNL

Abstract

Reducing energy usage in commercial buildings is a problem of interest to both building owners and governments seeking to reduce greenhouse gas emissions. In this paper, we propose automated methods of identifying certain energy efficiency opportunities in commercial buildings using only whole-building electricity consumption and local climate data. Our two-step approach uses piecewise linear regression and density-based clustering to detect both schedule- and operation-related electricity consumption faults. We demonstrate the effectiveness of the methodology using data collected from several commercial buildings.