A Framework for Automatically Extracting Overvoltage Features Based on Sparse Autoencoder

With the development of smart grid, it is of increasing significance to identify and cope with various types of overvoltages, faults and power quality disturbances effectively and automatically. In this paper, a framework for overvoltage identification and classification based on sparse autoencoder is proposed. By using single-layer and stacked sparse autoencoders, dimensionality reduction and automatic feature extraction of ferroresonance overvoltage waveforms in power distribution systems are achieved as an example, which does not require feature engineering to produce a series of features. Classification of different ferroresonance modes is then implemented with a softmax classifier, and favorable classification results are obtained after parameters of feature extraction and classifier models are determined. Application of the proposed framework in smart grids is discussed. The proposed framework provides a brand new idea for establishing a smart identification and classification system for overvoltages, which can be generalized to classification of faults and power quality disturbances.