Neural Networks Applied to Solve the Voltage Sag State Estimation Problem: An Approach Based on the Fault Positions Concept

Abstract

In this paper, the application of neural networks is proposed to solve the problem of voltage sags state estimation. This problem is based on estimating the voltage sags occurrence frequency at non monitored buses from the recorded voltage sags occurrence frequency at a limited number of monitored buses. The fault position method is used to formulate the optimization problem. The methodology is implemented by using Neural Networks routines from the Matlab® Neural Network ToolboxTM. Several case studies are showed in the IEEE-24 bus Reliability Test System (RTS).