A Sensor Fault Detection and Imputation Framework for Electrical Distribution Grids.

Automated and smart methods for monitoring and controlling the low voltage grid are required in the future to ensure safe operations in the presence of increasingly fluctuating power generation caused by distributed energy resources and power peaks caused by a rising number of electrical vehicles. These algorithmic methods rely on accurate (real-time) data, which has to be collected by sensors across the grid. As sensor faults can render these algorithms useless and lead to fatal failures in control, a suitable framework for sensor fault detection and imputation needs to be implemented. In this contribution, we evaluate how a data-driven virtual sensor-based imputation strategy can solve this task in a case study on the cigre distribution grid.