Classification of Power Quality Disturbances via Deep Learning

In this paper, a deep learning-based method is introduced into the classification of power quality disturbances (PQDs). Stacked autoencoder, as a deep learning framework, is employed to extract high-level features of PQDs for classification. In this context, a previously unsolved issue regarding optimal features’ selection for PQDs can be addressed. Besides, variances of signals and a particle swarm optimization algorithm are applied to assist classification of the PQDs. To sufficiently validate the effectiveness of the proposed classification scheme, a 10-fold cross-validation has been done. Experimental results indicate that the proposed approach is robust against noise and reaches a desirable classification accuracy rate.