Data Driven Transformer Level Misconfiguration Detection in Power Distribution Grids

Abstract

As more novel devices are integrated into the electricity grid due to the changes taking place in the energy system, ways of detecting deviations from the intended settings are needed. If misconfigurations of, for example, reactive power control curves of inverters go unnoticed, the safe and reliable operation of the power grid can no longer be ensured due to possible voltage violations or overloadings. Therefore, methods of detection of misconfigurations of said inverters using operational data at transformers are presented and compared. These methods include preprocessing by dimensionality reduction as well as detection by supervised learning approaches. The data used is of high reliability as it was collected in a lab setting reenacting typical and relevant grid operation situations. Furthermore, this data was recreated by simulation to validate the simulation data, which could also potentially be used for detection applications on a bigger scale. The results for both data sources were compared and conclusions drawn about applicability and usability for grid operators.