Wavelet Analysis and Radial Basis Function Neural Network Based Stability Status Prediction Scheme

Frimpong, Emmanuel Asuming (Dept. Electrical and Electronic Engineering, Kwame Nkrumah University of Science and Technology)
Okyere, Philip Yaw (Dept. Electrical and Electronic Engineering, Kwame Nkrumah University of Science and Technology)
Asumadu, Johnson (Dept. of Electrical and Computer Engineering, Western Michigan University)

JURNAL NASIONAL TEKNIK ELEKTRO
Vol 7, No 3: November 2018

This paper presents a technique for predicting the transient stability status of a power system. Bus voltages of system generators are used as input parameter. The bus voltages are processed using wavelet transform. Daubechies 8 mother wavelet is employed to extract wavelet entropy of detail 1 coefficients. The sum of wavelet entropies is used as input to a trained radial basis function neural network which predicts the transient stability status. The IEEE 39-bus test system was used to validate the effectiveness and applicability of the technique. The technique is simple to apply and can be implemented in real-time. The prediction accuracy was found to be 86.5% for 200 test cases. Keywords : Radial basis function, Transient analysis and Wavelet transform