Preliminary results on using artificial neural networks for security assessment (of power systems)

Artificial neural network techniques (ANNs) are explored as a tool to assess the dynamic security of power systems. The basic role of ANNs is to provide assessment of the system's stability based on training examples from offline analysis. Such an assessment would be useful as an operations aid. In essence, ANNs interpolate among planning analysis data. The authors present the results of a study to assess the capability of ANNs to learn from offline stability analysis results and give stability assessments when queried with data representing the current system status. The important feature of the result is that correct stability assessments are provided by the ANN not only when it is queried with an element of the training set of data but also under other operating conditions.<
>