Voltage stability assessment and enhancement using artificial neural networks and reactive compensation

This paper demonstrates the use of artificial neural networks for voltage stability assessment and enhancement of a power system. The neural network is trained with data containing a variety of load patterns. The reactive compensation is applied via switchable shunt VAr support. Studies are conducted on the New England 39 bus power system. It is concluded that artificial can be used for assessment of the support needed for extending the margin, and to assess the extended stability margin with reasonable accuracy.