Unsupervised deep learning and analysis of harmonic variation patterns using big data from multiple locations

•A novel framework employing unsupervised deep learning and clustering for harmonic voltage variations.•Identification of common underlying patterns from harmonic voltage data at multiple locations.•Criterion for training a deep learning algorithm from data at one location, that is effective for feature extraction of data at all locations.•Empirical analysis approaches for obtaining pattern distribution maps, typical waveform sequences of different classes, and 2D feature maps by nonlinear embedding of high-dimensional feature vectors.•Results demonstrate practical applicability of the method for large harmonic voltage data analytics.•The method can be applied as the basis for a range of power-quality phenomena, like RMS voltage, frequency, unbalance, rapid voltage changes, and harmonic currents. 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. [Display omitted]