New Wigner--Ville Spectra Method Improves Power Grid Anomaly Detection

A new research paper proposes using Wigner--Ville Distribution Slice (WVDS) spectra for anomaly detection in power grids. This method analyzes voltage waveforms in real-time, aiming to identify disturbances as they occur. The WVDS approach, when combined with a baseline-normalized deviation score, demonstrated a lower false-alarm rate compared to traditional Fast Fourier Transform (FFT) methods, reducing pre-onset false alarms to 0.69%. While WVDS was more selective, it also missed more anomalies than FFT. AI

RANK_REASON Research paper published on arXiv detailing a new signal processing technique for anomaly detection. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• autoencoder
• fast Fourier transform
• FFT-BND
• RTE
• Wigner--Ville Distribution
• Wigner--Ville Distribution Slice Spectra
• WVDS

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →