Signal features for classification of power system disturbances using PMU data

Biswal, Milan; Hao, Yifan; Chen, Phillip; Brahma, Sukumar; Cao, Huiping; León, Phillip L. De

doi:10.1109/pscc.2016.7540867

Cited by 35 publications

(24 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this regard, both field data and simulated data can be used. If enough field events are not available, training data can be generated using dynamic simulation, and field data can be used for testing [19, 32, 33]. The event data set was generated by simulating multiple instances of events listed in Table 1.…”

Section: Resultsmentioning

confidence: 99%

Event‐driven frequency and voltage stability predictive assessment and unified load shedding

Singh

Fozdar

2019

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Event‐driven frequency and voltage stability predictive assessment and unified load shedding

Singh

Fozdar

2019

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…Building of the dataset starts from a comprehensive set of systematic time-domain simulations (of post-contingency power system dynamics), using the nominal network topology with specific loading levels [44][45][46]. The consumed power was set at 80%, 90%, 100%, 110% and 120% of the basic system load levels (for different system load levels, both generation and loads are scaled by the same ratio).…”

Section: Features Engineering and Statistical Processingmentioning

confidence: 99%

Power System Transient Stability Assessment Using Stacked Autoencoder and Voting Ensemble

et al. 2021

View full text Add to dashboard Cite

Increased integration of renewable energy sources brings new challenges to the secure and stable power system operation. Operational challenges emanating from the reduced system inertia, in particular, will have important repercussions on the power system transient stability assessment (TSA). At the same time, a rise of the “big data” in the power system, from the development of wide area monitoring systems, introduces new paradigms for dealing with these challenges. Transient stability concerns are drawing attention of various stakeholders as they can be the leading causes of major outages. The aim of this paper is to address the power system TSA problem from the perspective of data mining and machine learning (ML). A novel 3.8 GB open dataset of time-domain phasor measurements signals is built from dynamic simulations of the IEEE New England 39-bus test case power system. A data processing pipeline is developed for features engineering and statistical post-processing. A complete ML model is proposed for the TSA analysis, built from a denoising stacked autoencoder and a voting ensemble classifier. Ensemble consist of pooling predictions from a support vector machine and a random forest. Results from the classifier application on the test case power system are reported and discussed. The ML application to the TSA problem is promising, since it is able to ingest huge amounts of data while retaining the ability to generalize and support real-time decisions.

show abstract

“…Feature selection method is the most vital part of pattern recognition and classification [25,26]. There are different types of feature extraction methods exits in the literature but for different data sets the features also vary.…”

Section: Feature Extractionmentioning

confidence: 99%

“…For the classification of multiclass PQ events, total 45 features are extricated from the VMD output. These features are selected because they are found to be significantly distinguishable in many classification cases reported in [25,26].…”

Section: Feature Extractionmentioning

confidence: 99%

“…According to ELM learning theory, the feature mapping function h(a) is chosen from a set of non-linear piecewise continuous functions to approximate any continuous target function. Since during the learning phase, the ELM achieves ∥ h(a)β − F(a) ∥ = 0, and smallest norm ∥ β ∥ 2 of the output weights due to the constrained optimisation process is given in (25), it satisfies the universal approximation capability [29][30][31].…”

Section: Reduced Kernel Function-based Classifiers For Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Multiclass power quality events classification using variational mode decomposition with fast reduced kernel extreme learning machine‐based feature selection

Chakravorti¹,

Dash

2018

IET Science, Measurement & Technology

View full text Add to dashboard Cite

Signal features for classification of power system disturbances using PMU data

Cited by 35 publications

References 11 publications

Event‐driven frequency and voltage stability predictive assessment and unified load shedding

Event‐driven frequency and voltage stability predictive assessment and unified load shedding

Power System Transient Stability Assessment Using Stacked Autoencoder and Voting Ensemble

Multiclass power quality events classification using variational mode decomposition with fast reduced kernel extreme learning machine‐based feature selection

Contact Info

Product

Resources

About