Abstract
The power flow in distribution grids is becoming more complicated as reverse power flows and undesired voltage rises might occur under particular circumstances due to integration of renewable energy sources, increasing the occurrence of critical bus voltages. To identify these critical feeders the observability of distribution systems has to be improved. To increase the situational awareness of the power system operator data driven methods can be employed. These methods benefit from newly available data sources such as smart meters. This paper presents a voltage estimation method based on neural networks which is robust under complex load and in-feeder generation situations. A major advantage of the proposed method is that the power system does not have to be explicitly modeled.