NEURAL NETWORK BASED CONTINGENCY ANALYSIS

Michal Kolcun - Radoslav Benč - Peter Szathmáry

   In this article is proposed an Artificial Neural Network (ANN) based approach to Contingency Analysis in a power systems. Previous work [1] has shown that ANNs may be unable to solve the contingency analysis problem when implemented in a traditional way. In order to solve the problem, the authors propose an ANN approach to contingency analysis. The approach is based on a problem decomposition. For every high-voltage (HV) line, a local contingency analyser is trained separately. The local analyzers consist of two-hidden layer perceptrons trained by the backpropagation. The approach is tested on a sample 14-bus (21-lines) real power system. The results show that the new approach is much more efficient than the traditional one.

Keywords: neural network, backpropagation, multi-layer perceptron, contingency analysis, power system control

[full-paper]