This paper aims to introduce deep learning to the power quality community by reviewing the latest applications and discussing the open challenges of this technology. Publications covering deep learning to power quality are stratified in terms of application, type of data, and learning technique. This work shows that the majority of the deep learning applications to power quality are based on unrealistic synthetic data and supervised learning without proper labelling. Some applications with deep learning have already been solved by previous machine learning methods or expert systems. The main barriers to implementing deep learning to power quality are related to lack of novelty, low transparency of the deep learning methods, and lack of benchmark databases. This work also discusses that even with automatic feature extraction by deep learning methods, power quality expert knowledge is still needed to implement and analyse the results. The main research gaps identified in this work are related to the applications of semi-supervised learning, explainable deep learning and hybrid approaches combining deep learning with expert systems. Suggestions for overcoming the present limitations are: providing a stronger collaboration among the grid stakeholders and academy to keep track of power quality events; proper labelling and enlarging of datasets in deep learning methods; explaining the end-to-end decision making of deep learning methods; providing open-access databases for comparison purposes.

This article proposes a novel scheme for analyzing power system measurement data. The main question that 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 (DAE) followed by feature clustering. An 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 article include: 1) providing a new unsupervised deep feature learning approach for seeking possible underlying patterns of power system variation measurements and 2) proposing an effective empirical analysis approach for understanding the measurements through examining the underlying feature clusters and the associated reconstructed data by DAE.

This paper presents a visualisation method, based on deep learning, to assist power engineers in the analysis of large amounts of power-quality data. The method assists in extracting and understanding daily, weekly and seasonal variations in harmonic voltage. Measurements from 10 kV and 0.4 kV in a Swedish distribution network are applied to the deep learning method to obtain daily harmonic patterns and their distribution over the week and the year. The results are presented in graphs that allow interpretation of the results without having to understand the mathematical details of the method. The inferences given by the results demonstrate that the method can become a new tool that compresses power quality big data in a form that is easier to interpret.

This paper addresses the issue of automatically seeking and identifying daily, weekly and seasonal patterns in harmonic voltage from measurement data at multiple locations. We propose a novel framework that employs deep autoencoder (DAE) followed by k-mean clustering. The DAE is used for extracting principal features from time series of harmonic voltages. A new strategy is used for training the encoder in DAE from data at one selected location that is effective for subsequent feature extraction from data at multiple locations. To analyze the patterns, several empirical analysis approaches are applied on the clustered principal features, including the distribution of daily patterns over the week and the year, representative waveform sequences of individual classes, and feature maps for visualizing high-dimensional feature space through low-dimensional embedding. The proposed scheme has been tested on a dataset containing harmonic measurements at 10 low-voltage locations in Sweden for the whole year of 2017. Results show distinct principal patterns for most harmonics that can be related to the use of equipment causing harmonic distortion. This information can assist network operators in finding the origin of harmonic distortion and deciding about mitigation actions. The proposed scheme is the first to provide a useful analysis tool and insight for finding and analyzing underlying patterns from harmonic variation data at multiple locations.

This paper proposes a deep learning (DL) method for the identification of spectral patterns of timevarying 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.

Waveform distortion in general represent a widespread problem in electrified transports due to interference, service disruption, increased losses and ageing 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 paper proposes an application of unsupervised DL to measurements of railway pantograph quantities to identify waveform distortion patterns. Data consists 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 sub-second intervals. Results are explained among others by connecting the distribution of the clusters (determined by self-supervised method) to the dynamic operating conditions of the rolling stock. Resulting DAE performance are superior in terms of accuracy and comprehensiveness of spectral components compared to a more traditional principal component analysis (PCA) that was chosen as reference for comparison.