Power system topology verification using artificial neural networks: maximum utilization of measurement data

The paper deals with power system topology verification. The correct model of a power system topology is essential for different power system applications. There are different approaches to power system topology verification. One of these approaches assumes utilization of artificial neural networks (ANNs). This approach is considered in the paper, however in the paper one assumes maximal utilization of measurement data differently than in many other papers devoted to topology verification with use of ANNs. This assumption makes possible to increase a number of relationships and also to increase theoretical knowledge used in the verification process. A consequence is increasing a number of cases in which the correct verification decision can be taken. In the paper, a brief review of existing approaches to power system topology verification is presented. Then, the theoretical background of the new approach is given. After the method based on this approach is described an example of its utilization is presented. At the end, features of presented method are discussed.