Data-Driven Misconfiguration Detection in Power Systems With Transformer Profile Disaggregation

Rapid and necessary changes in the energy sector are leading to rise of new, decentralized devices for generation consumption electrical distribution grid. Such inverter-connected photovoltaic (PV) generators, heat pumps (HP), or electric vehicle supply equipment (EVSE). These new components make power grid operation more difficult as they display volatile behavior therefore also need provide grid-supporting functionalities. Distribution System Operators (DSOs) sure these functionalities performed correctly, order guarantee a safe reliable However, especially low voltage is still ill-equipped with sensors monitor. This contribution, therefore, presents data-driven application detection misconfigurations using data available at metering points substations selected measurement combination transformer load profile disaggregation approach. The assembled outlined both functional, scalable, easy integrate into current monitoring schemes. has not been designed yet novel. used were collected life-like laboratory setup recreated simulations be able test validate well method. Two use cases control functions considered; first one reactive PV inverters, other Demand Side Management (DSM) loads. results presented offer insights quality performance assembled. best achieved F-score 0.83, which serves future benchmark there no comparable found literature. Furthermore, influences individual methods approach explored well. conclusions drawn show that functional solution reasonable reliability can implemented tested here. serve decision support tool DSOs requiring only minimal adjustments sensing infrastructure.