On-line transient stability assessment using hybrid artificial neural network

On-line transient stability assessment of a power system is not yet feasible due to the intensive computation involved. Artificial neural network has been proposed as one of the approaches to this problem because of its ability to quickly map nonlinear relationships between the input data and the output. In this paper a hybrid neural network for TSA is proposed. The proposed hybrid neural network is composed of a Kohonen network and several radial-basis function (RBF) networks. It possesses properties of both kinds of networks. So, its ability of TSA is improved. The proposed hybrid neural network is applied for an actual power grid, the obtain results confirm the validity of the developed method. Also, a comparison between the proposed neural network and other ones is present, which indicates the efficiency of the proposed neural network.