Real-time estimation of multiple series capacitor quantity for transient stability energy margin improvement

This paper presents a method for real-time estimation of the multi series capacity reference quantity in order to enhance the power system transient stability energy margin using an artificial neural network in a power system. This paper has three parts. The first part is to determine suitable lines to be installed by a series capacitor. The second is to estimate energy margin using an ANN. The last is to estimate each series capacity reference quantity if the estimated energy margin is unstable in the former step. The proposed ANN learning rule is the modified Levenberg-Marquardt backpropagation using the concept of fuzzy membership function.