Voltage sag estimation in sparsely monitored power systems based on deep learning and system area mapping

This paper proposes a voltage sag estimation approach based on a deep convolutional neural network. The proposed approach estimates the sag magnitude at unmonitored buses regardless of the system operating conditions and fault location and characteristics. The concept of system area mapping is also introduced via the use of bus matrix, which maps different patches in input matrix to various areas in the power system network. In this way, relevant features are extracted at various local areas in the power system and used in the analysis for higher level feature extraction, before feeding into a fully-connected multiple layer neural network for sag classification. The approach has been tested on the IEEE 68-bus test network and it has been demonstrated that the various sag categories can be identified accurately regardless of the operating condition under which the sags occur.