Abstract
The massive deployment of smart meters and other customized meters has motivated the development of nonintrusive load monitoring (NILM) systems. This is the process of disaggregating the total energy consumption in a building into individual electrical loads using a single-point sensor. Most literature is oriented to energy saving. Nevertheless, activity of daily livings monitoring through NILM is recently receiving much interest. This proposal presents an event-based NILM algorithm of high performance for activity monitoring applications. This is divided into two stages: 1) an event detector and 2) an event classification algorithm. The first one does not need to be trained and shows a detection rate up to 94%. The event classification algorithm uses a novel load signature based on trajectories of active, reactive, and distortion power (PQD) to obtain general models of appliance classes using principal component analysis. The F1 score and the F0.5 score (the last one is more relevant to activity monitoring) draw values of 90.6% and 98.5, respectively.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call