APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN POWER-SYSTEM SECURITY AND VULNERABILITY ASSESSMENT

In a companion paper the concept of system vulnerability is introduced as a new framework for power system dynamic security assessment. Usin g the TEF method of transient stability analysis, the energy margin DE LTAV is used as an indicator of the level of security, and its sensiti vity to a changing system parameter p (partial derivative DELTAV/parti al derivative p) as indicator of its trend with changing system condit ions. These two indicators are combined to determine the degree of sys tem vulnerability to contingent disturbances in a stability-limited po wer system. Thresholds for acceptable levels of the security indicator and its trend are related to the stability limits of a critical syste m parameter (plant generation limits). Operating practices and policie s are used to determine these thresholds. In this paper the artificial neural networks (ANNs) technique is applied to the concept of system vulnerability within the recently developed framework, for fast patter n recognition and classification of system dynamic security status. A suitable topology for the neural network is developed, and the appropr iate training method and input and output signals are selected. The pr ocedure developed is successfully applied to the IEEE 50-generator tes t system. Data previously obtained by heuristic techniques are used fo r training the ANN.