With the increase in smart, LEED-certified buildings there comes an increase in the amount of time-series data generated by the sensor networks within these buildings. Extracting useful information from the sensor network data can pose a challenge. While diurnal and seasonal patterns of electrical demand are well known from traditional metering systems, smart building sensor networks can provide insight into abnormalities or previously unknown patterns in electrical demand. In this paper, we demonstrate how to mine the data for these unknowns through the analysis of the frequency components of the time-series electrical demand data. The data for this study was collected from an LEED-certified building over twelve consecutive months with separate data feeds for the electrical demand from the heating, A/C, ventilation, lighting and miscellaneous systems. We employed Fourier methods to transform the data from the time domain to the frequency domain and then used similarity measures to look for similarities and outliers among the differing systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.