Technology Overview:
Researchers at the University of Nevada, Reno have developed real-time grid event detection software that analyzes phasor measurement unit (PMU) data. The software uses singular value decomposition (SVD) to measure changes in rank signatures across PMU data signals (voltage, current, frequency). It employs Bayesian optimization to automatically adjust detection thresholds, providing quick, accurate identification of grid events. The method has been tested and validated with real-world data, delivering >99% accuracy and ultra-fast detection speed.
Further Details:
A. Ghasemkhani, Y. Liu, and L. Yang, “Real-time event detection using rank signatures of real-world PMU data,” in 2022 IEEE PES General Meeting, Denver, CO, USA, July, 2022. doi: 10.1109/PESGM48719.2022.9917156. (Link)
Benefits:
- Very Fast Detection: Quickly spots power events in under 0.08 ms.
- Highly Accurate: Detects events correctly more than 99% of the time.
- Easy to Use: Automatically finds the best settings to make detection reliable.
- Trustworthy Results: Uses power-grid knowledge to reduce false alarms.
- Better Grid Stability: Quickly identifies problems, helping operators respond faster and keep the grid running smoothly.
Applications:
Real-time detection of power-grid disturbances, enhancing reliability and rapid response in electric utilities, smart-grid monitoring systems, automated grid control, and wide-area situational awareness.
Implementation: The software is developed in Python, allowing it to function either as a standalone solution or integrated within other commercial software platforms. It operates independently and does not require additional proprietary software components.
