High-Accuracy Power Quality Disturbance Classification Using the Adaptive ABC-PSO as Optimal Feature Selection Algorithm

Power quality disturbance (PQD) is an important issue in electrical distribution systems that needs to be detected promptly and identified prevent the degradation of system reliability. This work proposes a PQD classification using novel algorithm, comprised artificial bee colony (ABC) particle swarm optimization (PSO) algorithms, called “adaptive ABC-PSO” as feature selection algorithm. The proposed adaptive technique applied combination ABC PSO then used A discrete wavelet transform extraction method, probabilistic neural network classifier. We found highest accuracy (99.31%) could achieved through nine optimally selected features out all 72 extracted features. Moreover, demonstrated high performance noisy environment, well real system. When comparing presented system’s previous studies, ABC-PSO optimal algorithm considered at high-range scale; therefore, can classify practical