Power system network observability determination using feedforward neural networks

This paper presents a new method for the determination of network observability of the power system using the neural networks. The network observability problem, related to the power system configuration or network topology, called the topological observability, is taken for the solution. The topological observability analysis is done utilizing a feedforward neural network (FFNN) model, based on multilayer perceptrons using the backpropagation algorithm. The proposed feed-forward neural network model has been tested on sample power systems and results are presented.