Learning-Based Real-Time Event Identification Using Rich Real PMU Data

TL;DR

This paper introduces a two-stage learning framework combining Markov transition fields and CNNs to accurately and robustly identify power system events in real-time using large-scale PMU data.

Contribution

It presents a novel two-stage approach that encodes temporal dependencies and applies CNNs for real-time event detection in power systems, handling data quality issues.

Findings

High identification accuracy demonstrated on real large-scale PMU data

Robustness against poor data quality confirmed

Effective encoding of temporal dependencies in PMU data

Abstract

A large-scale deployment of phasor measurement units (PMUs) that reveal the inherent physical laws of power systems from a data perspective enables an enhanced awareness of power system operation. However, the high-granularity and non-stationary nature of PMU time series and imperfect data quality could bring great technical challenges to real-time system event identification. To address these issues, this paper proposes a two-stage learning-based framework. At the first stage, a Markov transition field (MTF) algorithm is exploited to extract the latent data features by encoding temporal dependency and transition statistics of PMU data in graphs. Then, a spatial pyramid pooling (SPP)-aided convolutional neural network (CNN) is established to efficiently and accurately identify operation events. The proposed method fully builds on and is also tested on a large real dataset from several tens of PMU sources (and the corresponding event logs), located across the U.S., with a time span of two consecutive years. The numerical results validate that our method has high identification accuracy while showing good robustness against poor data quality.