A Data-driven Approach to Multi-event Analytics in Large-scale Power Systems Using Factor Model

TL;DR

This paper introduces a data-driven, factor model-based approach for real-time multi-event detection and recognition in large-scale power systems, leveraging high-dimensional data analysis and random matrix theory.

Contribution

It presents a novel method that combines principal components and residual analysis to identify multiple events and their details in power systems.

Findings

Successfully detects multiple events in IEEE 118-bus system

Accurately identifies event components and timing

Enhances real-time power system monitoring

Abstract

Multi-event detection and recognition in real time is of challenge for a modern grid as its feature is usually non-identifiable. Based on factor model, this paper porposes a data-driven method as an alternative solution under the framework of random matrix theory. This method maps the raw data into a high-dimensional space with two parts: 1) the principal components (factors, mapping event signals); and 2) time series residuals (bulk, mapping white/non-Gaussian noises). The spatial information is extracted form factors, and the termporal infromation from residuals. Taking both spatial-tempral correlation into account, this method is able to reveal the multi-event: its components and their respective details, e.g., occurring time. Case studies based on the standard IEEE 118-bus system validate the proposed method.