Identification of power system emergency actions using neural networks

Abstract

The authors discuss the use of supervised learning and associative memories in an application for protecting the power system during an emergency situation. Automatic devices based on artificial neural networks are proposed as an intelligent and fast tool to mitigate the consequences of the major disturbance in the power system, area that involves a lot of unsolved problems. To prove the concept, the artificial neural network was trained to perform generation rescheduling as a way to alleviate the line overloads. The IEEE-30 bus test system was used to demonstrate that a feedforward neural network with back propagation can detect the state of the power system by monitoring line flows from SCADA data and then, make recommended corrective actions.<>