Power system voltage stability monitoring using artificial neural networks with a reduced set of inputs

This paper presents an artificial neural network (ANN)-based approach for online monitoring of a voltage stability margin (VSM) in electric power systems. The VSM is calculated by estimating the distance from the current operation state to the maximum voltage stability limit point according to the system loading parameter. Using the Gram-Schmidt orthogonalization process along with an ANN-based sensitivity technique, an efficient feature selection method is proposed to find the fewest input variables required to approximate the VSM with sufficient accuracy and high execution speed. Many algorithms have already been proposed in the literature for voltage stability assessment (VSA) using neural networks; however, the main drawback of the previously published works is that they need to train a new neural network when a change in the power system topology (configuration) occurs. Therefore, the possibility of employing a single ANN for estimating the VSM for several system configurations is investigated in this paper. The effectiveness of the proposed method is tested on the dynamic models of the New England 39-bus and the southern/eastern (SE) Australian power systems. The results obtained indicate that the proposed scheme provides a compact and efficient ANN model that can successfully and accurately estimate the VSM considering different system configurations as well as operating conditions, employing the fewest possible input features.