POWER-SYSTEM NETWORK TOPOLOGY PROCESSING BASED ON ARTIFICIAL NEURAL NETWORKS

In this paper, a new approach for the determination of power system ne twork topology based on Artificial Neural Networks (ANN) has been sugg ested. For the determination of power system network topology, three m odels of ANN based on Multilayer perceptron using Backpropagation Algo rithm (BPA), Functional Link Network (FLN) and Counter propagation Net work (CPN) have been utilized and tested for both noisy as well as noi se free data sets. ANN models based on BPA, FLN and CPN have been test ed on IEEE 14-bus, IEEE 57-bus and a 75-bus practical Indian system. I t has been established that the CPN based model predicts network topol ogy more accurately as compared to the FLN and BPA based models in all test cases. Further, the CPN model is able to determine the network t opology even if the network is unobservable for which the conventional network topology algorithm [8] fail to determine the topology.