Real-time event detection and feature extraction using PMU measurement data

Xu, Tong; Overbye, Thomas J.

doi:10.1109/smartgridcomm.2015.7436311

Cited by 28 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, a number of papers have explored datadriven methods for event detection and identification using PMU data. The previous work in this area can be roughly classified into two categories based on the number of PMUs used for model development: Class I: each PMU is treated independently and a single PMU data stream for each event is assigned as one data sample [3]- [6]. In [3], a signal processing-based methodology consisting of the swinging door trending algorithm and dynamic programming was proposed to detect power events.…”

Section: Introductionmentioning

confidence: 99%

“…In [5], an empirical model decomposition was utilized to assess power system events using wide-area post-event records. In [6], principal component analysis (PCA) was used to detect abnormal system behavior and adopt system visualizations. Class II: Instead of using data from a single PMU, several papers perform event identification tasks using multiple PMU measurements, which integrate interactive relationships of different PMUs [7]- [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning-Based Real-Time Event Identification Using Rich Real PMU Data

Yuan

Guo

Dehghanpour

et al. 2021

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

Phasor measurement units (PMUs) are being widely installed on power transmission systems, which provides a unique opportunity to enhance wide-area situational awareness. One key application is to utilize PMU data for real-time event identification. However, taking full advantage of all PMU data is still an open problem. This paper proposes a novel event identification method using multiple PMU measurements and deep graph learning techniques. Unlike previous models that rely on single PMU and ignore the interactive relationships between different PMUs or use multiple PMUs but determine the functional connectivity manually, our method performs datadriven interactive graph inference. Meanwhile, to ensure the optimality of the graph learning procedure, our method learns the interactive graph jointly with the event identification model. Moreover, instead of generating a single statistical graph to represent pair-wise relationships among PMUs during different events, our approach produces different event identificationspecific graphs for different power system events, which handles the uncertainty of event location. To test the proposed datadriven approach, a large real dataset from tens of PMU sources and the corresponding event logs have been utilized in this work. The numerical results validate that our method has higher identification accuracy compared to the previous methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning-Based Real-Time Event Identification Using Rich Real PMU Data

Yuan

Guo

Dehghanpour

et al. 2021

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

show abstract

“…The non‐model based methods directly catch the instantaneous changes from the observed waveform, induced by the abrupt transition when the disturbance occurs. For example, principal component analysis has been used on PMU data to extract features and then obtain the disturbance information like type and intense [11]. In [12], support vector machine and wavelet analysis are adopted to identify the faulty‐section and faulty‐half.…”

Section: Related Workmentioning

confidence: 99%

Data‐driven online distributed disturbance location for large‐scale power grids

Yang¹,

Chen²,

Zhou³

et al. 2019

IET Smart Grid

View full text Add to dashboard Cite

Timely detecting disturbances and locating their sources are critical to the reliable operation of power grids. This capability enables operators to effectively diagnose disturbances over wide areas and earns time for remedial reactions. In this study, a travelling-wave based scheme, namely data-driven online distributed disturbance location (DODDL), is proposed to quickly detect disturbances and determine their geographic location in large-scale power grids when the grids' topology is not available. The proposed DODDL scheme consists of two function blocks: (i) a singular spectrum analysis-based change-point detection method, which can quickly detect disturbances and determine their arrival time at distributed sensors, and (ii) a novel temporal scanning algorithm, which can accurately determine the geographic location of the disturbance source point. Utilising field measurement data sets recorded by the frequency disturbance recorders from the frequency monitoring network, it is shown that the DODDL scheme is not only quicker and more robust to grid non-homogeneity than existing approaches, but also can capture and locate more subtle and concealed disturbances.

show abstract

“…These tools require considerable preprocessing of PMU data before visualising. In [6], the principal component analysis was done with PMU measurements to improve situational awareness about the chance of occurrence of any abnormal event. Grideye [7] is another situational awareness tool used for power system dynamics monitoring.…”

Section: Introductionmentioning

confidence: 99%

PQ chart: a real‐time situational awareness tool for transmission lines

Murali

Soman

2020

IET gener. transm. distrib.

View full text Add to dashboard Cite

A tool to visualise real-time phasor measurement unit (PMU) data of a transmission line is proposed, named PQ chart. It is a simple and intuitive visualisation aid for operator situational awareness. The use of PMU data helps in capturing both steady-state and dynamic behavioural aspects of the transmission line. The tool is based on basic active and reactive power equations of a transmission line. The locus of active and reactive power flow corresponds to a circle in which the radius depends on voltage regulation. If the circle is imagined as a wheel, then the spokes of it correspond to the voltage angular difference across the transmission line. The PMU data is plotted on this canvas and its progression in time is observed. The occurrence of power swings, angular and voltage instabilities lead to a trajectory on the chart. A system operator can be alerted when any such movement occurs. The tool provides a single view from which deciphering active power flow, reactive power flow, voltage regulation, and voltage angle difference across a line becomes easy for the operator. Case studies with PMU data of 400 kV transmission lines in the Indian grid are presented to illustrate the tool's capabilities.

show abstract

Real-time event detection and feature extraction using PMU measurement data

Cited by 28 publications

References 10 publications

Learning-Based Real-Time Event Identification Using Rich Real PMU Data

Learning-Based Real-Time Event Identification Using Rich Real PMU Data

Data‐driven online distributed disturbance location for large‐scale power grids

PQ chart: a real‐time situational awareness tool for transmission lines

Contact Info

Product

Resources

About