Residential Appliance Identification Based on Spectral Information of Low Frequency Smart Meter Measurements

A nonintrusive load monitoring (NILM) method for residential appliances based on uncorrelated spectral components of an active power consumption signal is presented. This method utilizes the Karhunen Love expansion to breakdown the active power signal into subspace components (SCs) so as to construct a unique information rich appliance signature. Unlike existing NILM techniques that rely on multiple measurements at high sampling rates, this method works effectively with a single active power measurement taken at a low sampling rate. After constructing the signature data base, SC level power conditions were introduced to reduce the number of possible appliance combinations prior to applying the maximum a posteriori estimation. Then, an appliances matching algorithm was presented to identify the turned-on appliance combination in a given time window. After identifying the turned-on appliance combination, an energy estimation algorithm was introduced to disaggregate the energy contribution of each individual appliance in that combination. The proposed NILM method was validated by using two public databases: 1) tracebase; and 2) reference energy disaggregation data set. The presented results demonstrate the ability of the proposed method to accurately identify and disaggregate individual energy contributions of turned-on appliance combinations in real households.