A NEW PROTECTION PATTERN FOR DISTRIBUTION SYSTEM POWER QUALITY TRAILS PREDICTION AND CLASSIFICATION
Main Article Content
This paper displays a novel protection scheme of salp swam optimization (SSO) and artificial neural network (ANN) for distribution system power quality (PQ) events prediction and classification. In the proposed approach, ANN is utilized in two phases with the ultimate objective of prediction and classification of the PQ events. In first phase, ANN is utilized for perceive the system signal healthy or unhealthy condition under different circumstances. In second phase, ANN plays out the classification of the unhealthy signals to recognize the right PQ event for assurance. Here, the second phase ANN learning method is upgraded by utilizing the SSO in context of the minimum error objective function. These proposed methods play an assessment procedure to ensure the system and arrange the correct PQ event which occurs in the distribution system. At that point, the proposed work is completed in the MATLAB/Simulink platform and the execution is evaluated by using the examination, at different systems like SSA-ANN, MUSIC-ANN, GA-ANN. This method gets a handle on that the joined execution of ANN-SSO is more achievable in power quality events prediction and classification.
 T. Jayasree, D. Devaraj and R. Sukanesh, Power quality disturbance classification using Hilbert transform and RBF networks, Neurocomputing