POWER SYSTEM NETWORK TOPOLOGY PROCESSINGBASED ON ARTIFICIAL NEURAL NETWORKS

Abstract

In this paper, a new approach for the determination of power system network topologybased on Artificial Neural Networks (ANN) has been suggested. For the determinationof power system network topology, three models of ANN based on Multilayer perceptronusing Backpropagation Algorithm (BPA), Functional Link Network (FLN) andCounterpropagation Network (CPN) have been utilized and tested for both noisy as wellas noise free data sets. ANN models based on BPA, FLN and CPN have been tested onIEEE l4-bus, IEEE 57-bus and a 75-bus practical Indian system. It has been establishedthat the CPN based model predicts network topology more accurately as compared to theFLN and BPA based models in all test cases. Further, the CPN model is able to determinethe network topology even if the network is unobservable for which the conventionalnetwork topology algorithm [8] fail to determine the topology.