A Semi-Supervised Approach for Power System Event Identification

TL;DR

This work tackles the problem of identifying specific power-system events from PMU data under limited labeled samples by developing a semi-supervised framework that leverages unlabeled data. It introduces physically interpretable features derived from modal analysis, built on synthetic PMU data generated with PSS/E, and systematically compares self-training, transductive SVM, and graph-based label spreading for pseudo-labeling. Across inductive and transductive settings, graph-based label spreading consistently outperforms the other methods, with performance improving as more unlabeled data are included. The study provides practical insights for deploying PMU-based event identification in real grids and releases an all-in-one package for data generation, feature extraction, and semi-supervised classification.

Abstract

Event identification is increasingly recognized as crucial for enhancing the reliability, security, and stability of the electric power system. With the growing deployment of Phasor Measurement Units (PMUs) and advancements in data science, there are promising opportunities to explore data-driven event identification via machine learning classification techniques. However, obtaining accurately-labeled eventful PMU data samples remains challenging due to its labor-intensive nature and uncertainty about the event type (class) in real-time. Thus, it is natural to use semi-supervised learning techniques, which make use of both labeled and unlabeled samples. %We propose a novel semi-supervised framework to assess the effectiveness of incorporating unlabeled eventful samples to enhance existing event identification methodologies. We evaluate three categories of classical semi-supervised approaches: (i) self-training, (ii) transductive support vector machines (TSVM), and (iii) graph-based label spreading (LS) method. Our approach characterizes events using physically interpretable features extracted from modal analysis of synthetic eventful PMU data. In particular, we focus on the identification of four event classes whose identification is crucial for grid operations. We have developed and publicly shared a comprehensive Event Identification package which consists of three aspects: data generation, feature extraction, and event identification with limited labels using semi-supervised methodologies. Using this package, we generate and evaluate eventful PMU data for the South Carolina synthetic network. Our evaluation consistently demonstrates that graph-based LS outperforms the other two semi-supervised methods that we consider, and can noticeably improve event identification performance relative to the setting with only a small number of labeled samples.

Figures (2)

• Figure 1: Overview of the proposed semi-supervised pipeline.
• Figure 2: The $(\mathcal{F}{1}, \mathcal{F}{2})$ pairs denote the selection of pseudo-labeling and validation classifiers.The $5^{\text{th}}$ percentile of AUC scores for different classifiers using pseudo-labels obtained from: (a) Self-training method with various base classifiers, (b) TSVM, and (c) LS. (d) Comparison between (GB, GB) and (LS, $K$NN) in terms of average, $5^{\text{th}}$, and $95^{\text{th}}$ percentile of AUC scores.