Synchrophasor-Based Islanding Detection for Distributed Generation Systems Using Systematic Principal Component Analysis Approaches

Abstract

Systematic principal component analysis (PCA) methods are presented in this paper for reliable islanding detection for power systems with significant penetration of distributed generations (DGs), where synchrophasors recorded by Phasor Measurement Units (PMUs) are used for system monitoring. Existing islanding detection methods such as Rate-of-change-offrequency (ROCOF) and Vector Shift are fast for processing local information, however with the growth in installed capacity of DGs, they suffer from several drawbacks. Incumbent genset islanding detection cannot distinguish a system wide disturbance from an islanding event, leading to maloperation. The problem is even more significant when the grid does not have sufficient inertia to limit frequency divergences in the system fault/stress due to the high penetration of DGs. To tackle such problems, this paper introduces PCA methods for islanding detection. Simple control chart is established for intuitive visualization of the transients. A Recursive PCA (RPCA) scheme is proposed as a reliable extension of the PCA method to reduce the false alarms for time-varying process. To further reduce the computational burden, the approximate linear dependence condition (ALDC) errors are calculated to update the associated PCA model. The proposed PCA and RPCA methods are verified by detecting abnormal transients occurring in the UK utility network.

Complex Power System Status Monitoring and Evaluation Using Big Data Platform and Machine Learning Algorithms: A Review and a Case Study

“…In our early work, some data-driven methods based on linear principal component analysis (PCA) [87] were applied in power system data analysis [88], setting up a distributed adaptive learning framework for wide-area monitoring, capable of integrating machine learning and intelligent algorithms in [89]. In order to handle power system dynamic data and nonlinear variables, dynamic PCA [90] and recursive PCA [91] were also developed to improve the model accuracy. It is worth mentioning that linear PCA is unable to handle all process variables due to the normal Gaussian distribution assumption imposed on them, and many extensions using neural networks have been developed [92,93].…”

Multivariate Statistics and Supervised Learning for Predictive Detection of Unintentional Islanding in Grid-Tied Solar PV Systems

“…Since the power system is a dynamically changing system, the system variables used for creating the reference PCA model change dynamically causing it to change with time also. To tackle this issue, a recursive PCA algorithm was developed in [29] for the same UK power system case. The reference PCA model was updated in every iteration and the detection Yes No results for abnormal transients verified its effectiveness over the simple PCA approach.…”

A PMU Based Islanding Detection Scheme Immune to Additive Instrumentation Channel Errors

“…References [4] and [5] have used frequency differences and voltage phase angle differences for islanding detection, respectively. Principal component analysis (PCA) on voltage magnitudes, phase angles, and frequency measurements have been investigated for reliable islanding detection in [5], [6]. Data mining techniques such as support vector machine (SVM) and decision trees (DTs) were applied for islanding detection in [7] and [8], respectively.…”