Voltage stability prediction on power networks using artificial neural networks

Abstract

The objective of this paper is to predict the secure or the insecure state of the power system network using a hybrid technique which is a combination of Artificial Neural Network (ANN) and voltage stability indexes. Voltage collapse or an uncontrollable drop in voltage occurs in a system when there is a change in the condition of the system or a system is overloaded. A Transference Index (TI) which acts as a voltage stability indicator has been formulated from the equivalent two-bus network of a multi-bus power system network, which has been tested on a standard IEEE 30-bus system and the result is validated with a standard Fast Voltage Stability Index (FVSI). FACTS devices in the critical bus have been considered for the improvement of the voltage stability of the system. An ANN based supervised learning algorithm has been conferred in this paper alongside Contingency Analysis (CA) for the prediction of voltage security in an IEEE 30-bus power system network.