Implicit Neural Representation of Waveform Measurements in Power Systems Waveform Data Analysis

TL;DR

This paper introduces a novel implicit neural representation approach for modeling power system waveforms, enabling more accurate and compressed waveform analytics for applications like fault detection and oscillation monitoring.

Contribution

It develops sinusoidal-activation INR models tailored for power system waveforms, including extensions for correlated waveforms, demonstrating improved accuracy and compression in real-world cases.

Findings

Achieves <1-2% MSE accuracy in waveform modeling

Provides 4-6x compression of waveform data

Effective in oscillation monitoring applications

Abstract

There is currently a paradigm shift in several power system monitoring applications, such as incipient fault detection and monitoring inverter-based resources, to transition from traditional phasor analytics to more informative waveform analytics. This paper contributes to this transition by developing a novel approach to modeling voltage and current waveform measurements using implicit neural representations (INRs). INRs are continuous function approximators that are recently used in vision and signal processing. The proposed INR models are specifically designed to meet the requirements of waveform analytics in power systems, such as by using sinusoidal activation functions that capture the periodic nature of voltage and current waveforms. We also propose extended models that can efficiently represent correlated waveforms, such as three-phase waveforms and synchro-waveforms. Real-world case studies demonstrate the effectiveness of the proposed INR models in terms of accuracy (<1-2% MSE) and model size (4-6x compression). We also investigate the application of INR models in oscillation monitoring, for single mode oscillations and dual mode modulated oscillations.