APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN VOLTAGE STABILITY ASSESSMENT

Voltage stability problems have been one of the major concerns for ele ctric utilities as a result of system heavy loading. This paper report s on an investigation on the application of ANNs in voltage stability assessment. A multi-layer feed-forward artificial neural network (ANN) with error back-propagation learning is proposed for calculation of v oltage stability margins (VSM). Based on the energy method, a direct m apping relation between system loading conditions and the VSMs is set up via the ANN. A systematic method for selecting the ANN's input vari ables was developed using sensitivity analysis. The effects of ANN's t raining pattern sensitivity problems were also studied by dividing sys tem operating conditions into several loading levels based on sensitiv ity analysis. Extensive testing of the proposed ANN-based approach ind icate its viability for power system voltage stability assessment. Sim ulation results on five test systems are reported in the paper.