Event Detection in Micro-PMU Data: A Generative Adversarial Network Scoring Method

TL;DR

This paper introduces unsupervised deep learning models based on GANs for event detection in micro-PMU data, significantly improving accuracy over existing statistical methods without requiring extensive human input.

Contribution

It presents a novel GAN-based unsupervised approach for micro-PMU event detection, including an enhanced version with additional feature analysis, outperforming prior statistical methods.

Findings

Both methods outperform state-of-the-art statistical techniques.

The enhanced method achieves higher detection accuracy.

The models effectively detect point and group signatures in real-world data.

Abstract

A new data-driven method is proposed to detect events in the data streams from distribution-level phasor measurement units, a.k.a., micro-PMUs. The proposed method is developed by constructing unsupervised deep learning anomaly detection models; thus, providing event detection algorithms that require no or minimal human knowledge. First, we develop the core components of our approach based on a Generative Adversarial Network (GAN) model. We refer to this method as the basic method. It uses the same features that are often used in the literature to detect events in micro-PMU data. Next, we propose a second method, which we refer to as the enhanced method, which is enforced with additional feature analysis. Both methods can detect point signatures on single features and also group signatures on multiple features. This capability can address the unbalanced nature of power distribution circuits. The proposed methods are evaluated using real-world micro-PMU data. We show that both methods highly outperform a state-of-the-art statistical method in terms of the event detection accuracy. The enhanced method also outperforms the basic method.