2019
DOI: 10.1016/j.ijepes.2018.10.024
|View full text |Cite
|
Sign up to set email alerts
|

Through the looking glass: Seeing events in power systems dynamics

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
17
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
1
1

Relationship

1
8

Authors

Journals

citations
Cited by 31 publications
(18 citation statements)
references
References 27 publications
0
17
0
1
Order By: Relevance
“…Operators need mental representations of the data to be created and, after that, analyze them in order to extract more efficient information. A visualization way (i.e., the physical understanding of these internal representations) can make a considerable advancement in the facility of comprehension [10], [34]. Now, for making this possible, there is proper hardware for modern graphical user interfaces, but enough representations of these approaches are not currently implemented.…”
Section: Power Systems Visualizationmentioning
confidence: 99%
See 1 more Smart Citation
“…Operators need mental representations of the data to be created and, after that, analyze them in order to extract more efficient information. A visualization way (i.e., the physical understanding of these internal representations) can make a considerable advancement in the facility of comprehension [10], [34]. Now, for making this possible, there is proper hardware for modern graphical user interfaces, but enough representations of these approaches are not currently implemented.…”
Section: Power Systems Visualizationmentioning
confidence: 99%
“…Physically capturing the internal representations of data brings significant advances in pattern discovery and anomaly detection. There are few research efforts to implement data visualization technologies in power systems [21], [22]; however, more attention should be paid to this important goal.…”
Section: Introductionmentioning
confidence: 99%
“…A proper method for detecting and identifying suspect measurements is required. This paper will not treat these methods in detail, which can be obtained by a residual analysis, such as in [31] and [32] for bad data detection, or with other techniques based on artificial intelligence such as in [33] for system transitions. In this work, the standard normalized residual analysis [31], [32] triggers the identification of suspect samples for gross errors, while the system transitions are assumed as known.…”
Section: Suppression Of Suspect Samples and System Transitions Through Parzen Window Adjustmentmentioning
confidence: 99%
“…Estudos recentes apresentam o uso de imagens facilmente reconhecíveis para identificação de fenômenos de Qualidade de Energia (MIRANDA, 2019). Essas imagens podem ser geradas através de algoritmos de Deep Learning e Redes Neurais.…”
Section: Reconhecimento De Padrão E Visualização De Fenômenos De Qualunclassified