Waveform distortion in general represents a widespread problem in electrified transports due to interference, service disruption, increased losses, and aging of components. Given the multitude of moving sources and the extremely variable operating conditions, short-time records must be considered for analysis, and this increases in turn its complexity, from which the need for effective automated processing, as offered by a deep learning (DL) approach. This article proposes an application of unsupervised DL to measurements of railway pantograph quantities to identify waveform distortion patterns. Data consist of pantograph current from a Swiss 15-kV 16.7-Hz railway system. Three DL input types are considered: waveforms, harmonic spectra, and supraharmonic spectra. The applied DL method applied is the deep autoencoder (DAE) followed by feature clustering, using techniques to define a suitable number of clusters. Short-term distortion is evaluated over sub-10-min intervals of harmonic and supraharmonic spectra down to subsecond intervals. Results are explained among others by connecting the distribution of the clusters (determined by the self-supervised method) to the dynamic operating conditions of the rolling stock. The resulting DAE performance is superior in terms of accuracy and comprehensiveness of spectral components compared to a more traditional principal component analysis (PCA) that was chosen as a reference for comparison.

This paper proposes a novel scheme for analyzing power system measurement data. The main question we seek answers in this study is on “whether one can find some important patterns that are hidden in the large data of power system measurements such as variational data”. The proposed scheme uses an unsupervised deep feature learning approach by first employing a deep autoencoder followed by feature clustering. Analysis is performed by examining the patterns of clusters, and reconstructing the representative data sequence for the clustering centers. The scheme is illustrated by applying it to the daily variations of harmonic voltage distortion in a low-voltage network. The main contributions of the paper include: 1) providing a new unsupervised deep feature learning approach for seeking possible underlying patterns of power system variation measurements; 2) proposing an effective empirical analysis approach for understanding the measurements through examining the underlying feature clusters and the associated reconstructed data by deep autoencoder.

This paper proposes a deep learning (DL) method for the identification of spectral patterns of time-varying waveform distortion in photovoltaic (PV) installations. The PQ big data with information on harmonic and/or interharmonics in PV installations is handled by a deep autoencoder followed by feature clustering. Measurements of voltage and current from four distinct PV installations are used to illustrate the method. This paper shows that the DL method can be used as a starting point for further data analysis. The main contributions of the paper include: (a) providing a novel DL method for finding patterns in spectra; (b) guiding the manual post-processing based on the patterns found by the DL method; and (c) obtaining information about the emission from four PV installations.

Sufficient fault ride-through (FRT) of large wind power plants (WPPs) is essential for the operation security of transmission system. The majority of studies on FRT do not include all disturbances originating in the transmission system or the disturbances irrelevant to the operation security. Based on the knowledge of power quality, this paper provides a guide to stakeholders in different aspects of FRT for wind turbines (WTs) and WPPs. This paper details the characteristics of the most common disturbances originated in the transmission system, how they propagate to the WT terminals, and how they impact the dynamic behavior of a large WPP. This paper shows that the details of the voltage disturbances, not only in the transmission system, but also at the WT terminals, should be taken into consideration. Moreover, a detailed representation or characterization of voltage dips is important for FRT studies, despite that the simplified models used in the literature are insufficient. This paper strongly recommends that distinct events and additional characteristics such as the phase-angle jump and oscillations in the transition segments should be considered in FRT analysis.

Two important short-term voltage variation monitoring standards have recently been updated: IEEE 1564 and Distribution Procedures Module 8 (PRODIST) of the Brazilian National Regulatory Agency (ANEEL). The present work deals with a comparative analysis of both regulatory procedures, within the scope of the indices and reference standards implemented for the case of voltage sags. In order to achieve such a comparison, case studies of voltage sags are studied. Thus, in addition to showing the main updates and differences between the standardizations, the limitations on the classification of events by each case study case are also highlighted.