Effective identification of distributed energy resources using smart meter net?demand data

International policies and targets to globally reduce carbon dioxide emissions have contributed increasing penetration of distributed energy resources (DER) in low-voltage distribution networks. The growth technologies such as rooftop photovoltaic (PV) systems electric vehicles (EV) has, date, not been rigorously monitored record keeping is deficient. Non-intrusive load monitoring (NILM) methods contribute the effective integration clean within existing In this study, a novel NILM method developed for identification DER electrical signatures from smart meter net-demand data. Electrical profiles EV PV are allocated aggregated measurements including conventional appliances. Data several households United States used train test classification regression models. usage machine learning techniques provides proposed algorithm with fast processing times low system complexity, key factors needed differentiate highly variable power other loads. results confirm effectiveness methodology individually classify performance metrics 96% 99% PV. This demonstrates potential an embedded function meters increase observability