Neural Network Approach for Estimation of Peak Over voltages Under Switching Transients

Sulabh Khandelwal

Abstract: Intended transmission line switching operations are required for charging the lines for restoration of power following some disturbances. Though detailed transient studies carried out for the design of transmission lines, such studies are not common in a day-today operation of power systems.However it is important for the operator to ensure that peak overvoltages resulting from the switching operations are well within safe limits. This paper presents an Artificial Neural Network (ANN) based approach to estimate the peak overvoltages generated by switching transients. In the proposed methodology Levenberg-Marquardt method is used to train the multilayer perceptron. The developed ANN is trained with the extensive simulated results, and tested for typical cases. The results presented for a 400 kV system show that the proposed approach can estimate the peak values of switching overvoltages with good accuracy. Index Terms- Artificial neutral networks, electromagnetic transients, switching surges.