Red deer optimized recurrent neural network for the classification of power quality disturbance

Power Quality Disturbance (PQD) in a power grid distribution destroys the quality of to user. Thus, early detection disturbances is essential diagnose network before failure. Several may cause voltage sag, swell, or occurrence both. In proposed method deep recurrent neural (DRNN) used for classifying PQD as well Red Deer Optimization (RDO) algorithm optimizing weight from DRNN. Based on behaviour deer roaring rate will optimize DRNN RDO. Signal processing done by S-transform (ST) because better performance signals terms high order noise. The implemented Simulink tool and results are compared with existing methods. result shows that classified accuracy 99.95% precision 99.98% higher than