.png){kind=icon}
.png){kind=icon}
Return
A Higher-Order Tensor Enhanced Algorithm for Synchrophasor Data Anomaly Identification
.png){kind=icon}
PRE
AI
DOI：10.1109/TPWRS.2026.3666692.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Identifying anomalies in Phasor Measurement Unit (PMU) data is of critical importance. Existing methods can be broadly categorized into model-based and data-driven ones. The former requires an accurate system model, while the latter resorts to specific statistical assumptions, such as the Gaussian, symmetric, or single-mode, etc, which may not hold in practice. In view of this, we propose a data-driven anomaly identification method using the fourth-order cumulant. Its tensor structure can intrinsically preserve the tail characteristics of PMUs data, thereby inherently revealing latent anomalies without assuming any statistical distributions. Additionally, we incorporate Copula to distinguish anomalies from system events or measurement outliers. Simulation results on real-world PMU data demonstrate the excellent performance of the proposed method.
Keywords:
Anomaly identification
cumulant tensor
PMU
Journal
IF:
7.2
Papers:
1.1W
Citations:
5.0W