Artificial neural networks for on-line voltage stability assessment

Voltage stability has recently become a challenging problem for many power systems. Voltage instability can be ascribed to the lack of reactive power support needed to maintain the voltage profile at a specified value. It has been responsible for severe system disturbances including major blackouts. A key concept in the restructuring of the electric power industry is the ability to accurately and rapidly quantify the capabilities of transmission systems. Computation of Available Transmission Capability (ATC) must take into account adequate static, dynamic, and voltage stability margins. On-line voltage stability assessment tools will be required for the secure operation of interconnected power systems. This paper presents the application of Artificial Neural Networks (ANN) for on-line voltage stability assessment. A key feature of the proposed method is the use of principal component analysis to project the input patterns in the original pattern space into a new subspace having fewer dimensions than the original pattern space. This enhances the efficiency of ANN training. The proposed neural network is used to determine the voltage stability margin of the IEEE 118 bus power system for different operating conditions. The possibility of including topology information in a single ANN is also investigated.