New algorithm for identifying network topology based on artificial neural networks

Correct insight and interpretation of the network topology are crucial task of any state estimator. In order to improve state estimators accuracy and speed, a new approach of determining network topology is presented. Presented method is based on measurement of the injected test signal reflection from the impedance discontinuities in the network. Correct interpretation of the measured reflected signal gives possibility to determine the network topology at the reflection site. This paper presents interpretation of the reflected signal by the developed artificial neural network (ANN). The ANN system has been used for identifying a network topology of modeled and simulated certain part of Croatian transmission system. The results are displayed as a receiver operating characteristic (ROC) curve form for the best and worst prediction case.