Published October 29, 2019 | Version v1
Conference paper Open

EMD and Gradient Boosting Regression for NILM at Residential Houses

  • 1. Information Technologies Institute/ The Centre for Research and Technology Hellas


Abstract— In this paper a novel appliance load estimation in a non-intrusive way is presented. The proposed algorithm includes signal processing techniques such as filtering and Empirical Mode Decomposition (EMD) which is used to decompose random noise from the power consumption data collected from the smart meter. Lag features that capture the variance of the data across time are utilized. Experimental results which showcase the effectiveness of the suggested method are also presented.



Additional details


DELTA – Future tamper-proof Demand rEsponse framework through seLf-configured, self-opTimized and collAborative virtual distributed energy nodes 773960
European Commission