Application of artificial neural networks for security assessment of medium size power systems

Isolated electrical power systems face specific problems related to their operation and control. Some of the most important ones are related to the system dynamic stability. It is therefore apparent the need for a fast dynamic security assessment (DSA) function, in order to improve system operation. In this paper ANNs of multilayer perceptron (MLP) architecture are applied for online DSA. It is shown that is proposed for better performance in DSA. The application of this technique on the power system of Crete is shown to provide online maximum frequency deviations and maximum frequency change rates in case of pre-specified contingencies.