Simultaneous online identification and localization of disturbances in power transmission systems

Kummerow, André; Monsalve, Cristian; Nicolai, Steffen; Bretschneider, Peter

doi:10.1109/isgteurope.2019.8905711

Cited by 9 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Within this study, recurrent neural networks are used to efficiently process and analyse the highdimensional PMU data records and to learn discriminative feature embeddings. The use of gating mechanisms in gated recurrent units (GRU) or long short-term memory (LSTM) cells enables backpropagation over long time periods and [27].…”

Section: Siamese Recurrent Neuronal Network With Double-sigmoid Classifiersmentioning

confidence: 99%

“…Based on previous work in [27], a single prediction model approach is used to identify and locate disturbances by analysing measurement signals from several PMUs, which are distributed over the grid. The analysis of the spatiotemporal relationships between different PMU signals allows to classify disturbance events, which are not directly observable by PMUs and therefore make the classification approach somewhat independent from a specific PMU placement.…”

Section: Classification Models Considering Unknown Disturbance Eventsmentioning

confidence: 99%

“…The computation time for recurrent neural network cells is very low compared to other feature extraction techniques (e.g. dynamic time warping (DTW) or time‐frequency transformations) due to the simple matrix calculations, which enables a fast online processing and classification of the PMU data streams [27].…”

Section: Classification Models Considering Unknown Disturbance Eventsmentioning

confidence: 99%

“…The computation time for recurrent neural network cells is very low compared to other feature extraction techniques (e.g. dynamic time warping (DTW) or time-frequency transformations) due to the simple matrix calculations, which enables a fast online processing and classification of the PMU data streams[27].The general model architecture of the proposed Siamese recurrent neural network-based classifier is given in Figure2. The support X S and query instances X Q are fed into a GRU layer to compute the corresponding hidden state matrices H S and H Q .Q by the use of attention mechanisms.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Siamese recurrent neural networks for the robust classification of grid disturbances in transmission power systems considering unknown events

2021

Self Cite

View full text Add to dashboard Cite

The automated identification and localisation of grid disturbances is a major research area and key technology for the monitoring and control of future power systems. Current recognition systems rely on sufficient training data and are very error-prone to disturbance events, which are unseen during training. This study introduces a robust Siamese recurrent neural network using attention-based embedding functions to simultaneously identify and locate disturbances from synchrophasor data. Additionally, a novel doublesigmoid classifier is introduced for reliable differentiation between known and unknown disturbance types and locations. Different models are evaluated within an open-set classification problem for a generic power transmission system considering different unknown disturbance events. A detailed analysis of the results is provided and classification results are compared with a state-of-the-art open-set classifier.

show abstract

Section: Siamese Recurrent Neuronal Network With Double-sigmoid Classifiersmentioning

confidence: 99%

Section: Classification Models Considering Unknown Disturbance Eventsmentioning

confidence: 99%

Section: Classification Models Considering Unknown Disturbance Eventsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Siamese recurrent neural networks for the robust classification of grid disturbances in transmission power systems considering unknown events

2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…First investigations of a simultaneous disturbance identification and localization were performed in [58] by comparing five different classification approaches. From these results and additional research [59], recurrent neural networks were rated as very suitable for the online classification of grid disturbances regarding the classification accuracy and prediction time.…”

Section: Disturbance Classificationmentioning

confidence: 99%

A Novel Framework for Synchrophasor Based Online Recognition and Efficient Post-Mortem Analysis of Disturbances in Power Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Synchrophasor based applications become more and more popular in today’s control centers to monitor and control transient system events. This can ensure secure system operation when dealing with bidirectional power flows, diminishing reserves and an increased number of active grid components. Today’s synchrophasor applications provide a lot of additional information about the dynamic system behavior but without significant improvement of the system operation due to the lack of interpretable and condensed results as well as missing integration into existing decision-making processes. This study presents a holistic framework for novel machine learning based applications analyzing both historical as well as online synchrophasor data streams. Different methods from dimension reduction, anomaly detection as well as time series classification are used to automatically detect disturbances combined with a web-based online visualization tool. This enables automated decision-making processes in control centers to mitigate critical system states and to ensure secure system operations (e.g., by activating curate actions). Measurement and simulation-based results are presented to evaluate the proposed synchrophasor application modules for different use cases at the transmission and distribution level.

show abstract

Robust disturbance classification in power transmission systems with denoising recurrent autoencoders

Kummerow

Dirbas

Monsalve

et al. 2022

Sustainable Energy, Grids and Networks

View full text Add to dashboard Cite

Simultaneous online identification and localization of disturbances in power transmission systems

Cited by 9 publications

References 12 publications

Siamese recurrent neural networks for the robust classification of grid disturbances in transmission power systems considering unknown events

Siamese recurrent neural networks for the robust classification of grid disturbances in transmission power systems considering unknown events

A Novel Framework for Synchrophasor Based Online Recognition and Efficient Post-Mortem Analysis of Disturbances in Power Systems

Robust disturbance classification in power transmission systems with denoising recurrent autoencoders

Contact Info

Product

Resources

About