Marvelous Significance Performance Analysis of PQ Events Prediction and Classification

This paper compares various significant research techniques concerning the Power Quality (PQ) events prediction and classification system presented by the authors previously and examines its viability scale as far as the research gap. This paper examines some of the frequently exercised PQ classification techniques named as Feedforward Neural Network (FNN), Sequential Ant Lion Optimizer and Recurrent Neural Network (SALRNN), dual-layer Feedforward network and Short-Time Fourier Transform (STFT) ) from the most significant literature in order to have more insights of the techniques. The research work has presented a simple framework that retains a balance between higher accuracy in the detection of disturbances as well as also maintains an effective computational performance for a large number of the power signals. The principle aim of the paper is research and comparative analysis of above-mentioned algorithms for searching the best impressive technique in detecting and classifying the PQ events. The simulation results of this research can be reasoned that the SALRNN technique detects and classifies accurately the PQ disturbances when compared with the other two techniques such as FNN and STFT.