NILM (Non-intrusive Load Monitoring), or NALM (Nonintrusive Appliance Load Monitoring), is a process for analyzing changes in the voltage and current going into a house and deducing what appliances are used in the house as well as their individual energy consumption. NILM is a concept known for more than 20 years. Despite the long presence of this concept, it has recently received considerable attention in the realm of energy conservation. In this domain, the main objective of NILM is to gain insights into electrical energy consumption of individual devices in private households. Therefore, NILM techniques aim at disaggregating consumption data and identifying individual appliances or groups of appliances.
This paper focuses on identifying which appliance is currently operating by analyzing electric load signature for home energy monitoring system. The identification framework is comprised of three steps. Firstly, specific appliance features, or signatures, were chosen, which are DC (Duty Cycle), SO (Slope of On-state), VO (Variance of On-state), and ZC (Zero Crossing) by reviewing observations from 13 houses for 3 days. Five appliances of electrical rice cooker, kimchi-refrigerator, PC, refrigerator, and TV were chosen for the identification with high penetration rate and long total operation time in Korea.
Secondly, K-NN and Naive Bayesian classifiers, which are commonly used in many applications, are employed to estimate from which appliance the signatures are obtained. Each signature is tested by each classification algorithm, so multiple estimates are resulted as candidates of final identification. Lastly, proposed framework selected one of candidates as final identification result by majority voting. The proposed identification frame showed identification success rate of 94.23%.