Power Quality Disturbances Recognition Based on Deep Residual Network

Abstract

Traditional power quality disturbances(PQDs) recognition methods are based on selecting features manually and then use classifiers to classify. For huge amounts of data, this method has the problem of insufficient features or redundant features, which leads to low recognition accuracy. With the development of deep learning technology, this paper proposes a PQDs identification method based on a deep residual network. This method links the two sets of convolutional layers in the traditional convolutional network into a residual block through short-cut. Then, it learns layer by layer through residual blocks, acquiring the deep features of data. Thus it realizes the identity mapping of the redundant layer by short-line connections to solve the network degradation problem of deep networks, and reduces the difficulty of network training. Finally, the softmax layer is used for classification. In order to test the anti-noise ability of the network, the deep residual network model is trained with the data added with Gaussian white noise. Simulation results show that, comparing with ordinary convolutional networks, the method proposed can accurately identify 7 types of single disturbances and 5 types of composite disturbances in different noise conditions. Furthermore, it has higher robustness and better network convergence speed.