Monitoring of voltage stability margins using artificial neural networks with a reduced input set

Abstract

In this paper, a new methodology is proposed for the on-line monitoring of voltage stability margins, using artificial neural networks with a reduced input data set from the power system. Within the framework of this methodology, first the system model is reduced using self-organized artificial neural networks and an extended AESOPS algorithm. Then supervised learning of multi-layered artificial neural networks is carried out on the basis of this reduced model. Finally, based on the trained network and the reduced set of system variables, monitoring of voltage stability margins is done. The proposed methodology is tested on a power system with 20 buses. The obtained results indicate the justifiability of using a reduced system because of the increased efficiency and quality of calculation, both in the learning stage and in the exploitation stage of the artificial neural network.