Detection and visualization of power system disturbances using principal component analysis

Barocio, E.; Pal, Bikash; Fabozzi, Davide; Thornhill, Nina F.

doi:10.1109/irep.2013.6629374

Cited by 35 publications

(22 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…How to extract such information from the measured data for disturbance detection and localization is an important issue for power system researchers [2]. Generally, the existing data-driven methods can be divided into three categories according to the applications: (1) for the protection of power system equipment, e.g., the wavelet coefficient energy based method [3] and the hidden Markov model based method [4]; (2) for the analysis of power quality especially the waveform of alternate voltage, e.g., the Hilbert-Huang transform based method [5] and the power quality state estimation based method [6]; (3) for the assessment of the system security and stability, typically by multivariate statistical analysis based methods [7]- [10].…”

Section: Wide-area Monitoring Of Power Systems Using Principalmentioning

confidence: 99%

Wide-Area Monitoring of Power Systems Using Principal Component Analysis and $k$-Nearest Neighbor Analysis

Cai

Thornhill

Kuenzel

et al. 2018

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

Wide-area monitoring of power systems is important for system security and stability. It involves the detection and localization of power system disturbances. However, the oscillatory trends and noise in electrical measurements often mask disturbances, making wide-area monitoring a challenging task. This paper presents a wide-area monitoring method to detect and locate power system disturbances by combining multivariate analysis known as Principal Component Analysis (PCA) and time series analysis known as k-Nearest Neighbor (kNN) analysis. Advantages of this method are that it can not only analyze a large number of wide-area variables in real time but also can reduce the masking effect of the oscillatory trends and noise on disturbances. Case studies conducted on data from a four-variable numerical model and the New England power system model demonstrate the effectiveness of this method.

show abstract

Section: Wide-area Monitoring Of Power Systems Using Principalmentioning

confidence: 99%

Wide-Area Monitoring of Power Systems Using Principal Component Analysis and $k$-Nearest Neighbor Analysis

Cai

Thornhill

Kuenzel

et al. 2018

IEEE Trans. Power Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…of Porto): My question is regarding the paper on "Detection and Visualization of Power System Disturbances using Principal Component Analysis" [3]. So you assume the data you get has normality structure and for that you do a χ-square test method just to test the hypothesis So have you found any situations where this normality condition does not apply, and if that happens how do you still rely on the approach based on the principal-component analysis?…”

Section: S Meliopoulosmentioning

confidence: 99%

“…Le Xie (Texas A&M): I have a question for the third paper [3]. The Principal Component Analysis (PCA) one.…”

Section: S Meliopoulosmentioning

confidence: 99%

Oral discussions on Session: “Control and protection” - Part II

Costa

2013

2013 IREP Symposium - Bulk Power System Dynamics and Control - IX Optimization, Security and Control of the Emerging Power Grid

View full text Add to dashboard Cite

show abstract

“…The same idea was also implemented in our previous work [5], but with an extended application in power system islanding detection as well as a fault reconstruction method that have been used to identify the islanding site based on the data collected from synchrophasors in a real system. Similarly, in a recent paper by Barocio et al [6], PCA was used for detecting and extracting unusual or anomalous events from wide-area monitoring data, demonstrating the ability to detect and extract system events based on a transient stability model of the New England Test System. All these researches adopt the PCA method to reduce the dimensionality of the big data to a certain extent.…”

Section: Introductionmentioning

confidence: 99%

Loss-of-Main Monitoring and Detection for Distributed Generations Using Dynamic Principal Component Analysis

Guo¹,

Li²,

Laverty³

2014

JPEE

View full text Add to dashboard Cite

In this paper, our previous work on Principal Component Analysis (PCA) based fault detection method is extended to the dynamic monitoring and detection of loss-of-main in power systems using wide-area synchrophasor measurements. In the previous work, a static PCA model was built and verified to be capable of detecting and extracting system faulty events; however the false alarm rate is high. To address this problem, this paper uses a well-known 'time lag shift' method to include dynamic behavior of the PCA model based on the synchronized measurements from Phasor Measurement Units (PMU), which is named as the Dynamic Principal Component Analysis (DPCA). Compared with the static PCA approach as well as the traditional passive mechanisms of loss-of-main detection, the proposed DPCA procedure describes how the synchrophasors are linearly auto-and cross-correlated, based on conducting the singular value decomposition on the augmented time lagged synchrophasor matrix. Similar to the static PCA method, two statistics, namely T 2 and Q with confidence limits are calculated to form intuitive charts for engineers or operators to monitor the loss-of-main situation in real time. The effectiveness of the proposed methodology is evaluated on the loss-of-main monitoring of a real system, where the historic data are recorded from PMUs installed in several locations in the UK/Ireland power system.

show abstract

Detection and visualization of power system disturbances using principal component analysis

Cited by 35 publications

References 15 publications

Wide-Area Monitoring of Power Systems Using Principal Component Analysis and $k$-Nearest Neighbor Analysis

Wide-Area Monitoring of Power Systems Using Principal Component Analysis and $k$-Nearest Neighbor Analysis

Oral discussions on Session: “Control and protection” - Part II

Loss-of-Main Monitoring and Detection for Distributed Generations Using Dynamic Principal Component Analysis

Contact Info

Product

Resources

About

Detection and visualization of power system disturbances using principal component analysis

Cited by 35 publications

References 15 publications

Wide-Area Monitoring of Power Systems Using Principal Component Analysis and $k$-Nearest Neighbor Analysis

Wide-Area Monitoring of Power Systems Using Principal Component Analysis and $k$-Nearest Neighbor Analysis

Oral discussions on Session: &#x201C;Control and protection&#x201D; - Part II

Loss-of-Main Monitoring and Detection for Distributed Generations Using Dynamic Principal Component Analysis

Contact Info

Product

Resources

About

Oral discussions on Session: “Control and protection” - Part II