Main Article Content

Single topology neural network-based voltage collapse prediction of developing power systems


J. N. Onah
C. O. Omeje
D. U. Onyishi
J. Oluwadurotimi

Abstract

Most modern power systems operate within the vicinity of saddle-node bifurcation points because the network operators are hard put to estimating the margin to voltage collapse before the blackout. As a result, voltage stability analysis and control are growing concerns amongst electric power utilities. The selection of the hidden layer units and the training function algorithms for back propagation artificial neural network training are major challenges. Hitherto, comparative analyses of the training functions were made. Thereafter, the complexity of the artificial neural network topology was made very simple by selecting the hidden layer neurons via scripts written in Matlab software environment. To obtain the hidden layer unit, a script has to be developed in MATLAB to select a hidden layer neuron from a range of 10 to 65. The result shows that the optimal 55 hidden units have root mean square error (RMSE) of 0.05. The result was validated when the range of hidden layer neurons was extended to 100. The proposed approach was tested in a typical developing power system: a 45-bus Nigerian 330kV transmission network and proved to be fast and accurate for voltage collapse prediction.


Journal Identifiers


eISSN: 2467-8821
print ISSN: 0331-8443