OLM software data set for Nonintrusive Load Monitoring (NILM)

Abstract

A Nonintrusive Load Monitoring system (NILM) is an energy demand monitoring with load identification system. The NILM can use only one instrument installed at main power distribution board for the monitoring and load identification. In this paper, we present the Operating Load Model data set (OLM), a software data set containing detailed electricity consumption that can be adjusted by user, which is aimed at furthering research on energy disaggregation. This paper points to six appliances in household including air conditioner, television, refrigerator, rice cooker, fluorescent lamp and electric iron. Moreover the paper implemented a low sampling rate of monitored data to detect any change of power signal that obtained a 1 Hz sampling rate of active power from OLM software data set. The proposed OLM used 5 points of recorded data with steady-state real power and reactive power signatures to disaggregation. From the results showed that the proposed OLM software data set can be used to test NILM algorithm and the proposed NILM algorithm can disaggregation energy of the OLM software data set in 6 cases with accuracy percentage of energy consumption is approximately 91.76%.