Steady‐state security prediction in presence of load uncertainty

Abstract

An important problem in the Electrical Power System operation is the steady-state security prediction. In order to take into account the load uncertainty, in this paper the authors apply a Monte-Carlo method together with an opportune Security Index to evaluate in a preventive manner the probability to fall in insecure operating state, by determining the security index probability density function. For this aim, in a previous paper proposed by the authors, it has been possible to take advantage of an Artificial Neural Network, trained to evaluate the Security Index probability density function in presence of the optimal economical dispatching of the generation powers for the load forecast. In the present paper, a more complex scenario is considered where the security analysis can suggest to the dispatcher to determine also non-optimal economical operating conditions to improve security. So a new, more complex, organization of the Artificial Neural Network training stage, necessary in order to obtain increased generalization capacity in the production stage, has been considered. In the first part of the paper the used security index, the Monte-Carlo simulation and the neural network structure with its learning algorithm utilized by the authors for the particular problem are briefly recalled. Finally, a numerical application on a simple electrical test system is shown pointing out very encouraging results.