M. Boudour and A. Hellal
Power system static security assessment, self-organizing feature map,growing hierarchical SOM, neural network classifier
This article presents an artificial neural-net based technique that combines supervised and unsupervised learning for evaluating online power system static security. It automatically scans contingencies of a power system. The proposed approach allows the online security evaluation of (N – 1) contingencies by considering the pre-fault state vector. ANN-based pattern recognition is carried out with growing hierarchical self-organizing feature mapping (GHSOM) in order to provide an adaptive neural net architecture during its unsupervised training process. Numerical tests, carried out on an IEEE 14-bus power system, are presented and discussed. The analysis using such method provides accurate results and improves the effectiveness of system security evaluation. It is especially suitable for the static security assessment of large-scale power systems.
Important Links:
Go Back
