2022
DOI: 10.3390/s22218323
|View full text |Cite
|
Sign up to set email alerts
|

Wavelet LSTM for Fault Forecasting in Electrical Power Grids

Abstract: An electric power distribution utility is responsible for providing energy to consumers in a continuous and stable way. Failures in the electrical power system reduce the reliability indexes of the grid, directly harming its performance. For this reason, there is a need for failure prediction to reestablish power in the shortest possible time. Considering an evaluation of the number of failures over time, this paper proposes performing failure prediction during the first year of the pandemic in Brazil (2020) t… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
18
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 40 publications
(18 citation statements)
references
References 88 publications
0
18
0
Order By: Relevance
“…Hybrid methods utilizing LSTM are widely implemented for time series forecasting problems, such as stock prediction [41], which results in improved prediction accuracy [42]. Hybrid versions of LSTM, such as wavelet LSTM, are better in time series prediction compared to the traditional methods used [43]. Trending models for enhanced time series forecasting were proposed in the electrical domain where researchers concluded that a wavelet adaptive neuro-fuzzy inference system outperformed other competent models such as the group method of data handling, LSTM, bootstrap aggregation, sequential learning, and many ensemble learning methods [44].…”
Section: Modern Methods Used For Forecastingmentioning
confidence: 99%
“…Hybrid methods utilizing LSTM are widely implemented for time series forecasting problems, such as stock prediction [41], which results in improved prediction accuracy [42]. Hybrid versions of LSTM, such as wavelet LSTM, are better in time series prediction compared to the traditional methods used [43]. Trending models for enhanced time series forecasting were proposed in the electrical domain where researchers concluded that a wavelet adaptive neuro-fuzzy inference system outperformed other competent models such as the group method of data handling, LSTM, bootstrap aggregation, sequential learning, and many ensemble learning methods [44].…”
Section: Modern Methods Used For Forecastingmentioning
confidence: 99%
“…The hybrid model improved the forecast accuracy by reducing the average absolute percentage error rate when compared to the base model [20]. The use of filters for noise reduction can improve the model's ability to make predictions, and besides seasonal filters, the wavelet transform shows promise for this purpose [21], and can be combined with several state-of-the-art models [22], or classical methods such as neuro-fuzzy systems [23].…”
Section: Related Workmentioning
confidence: 99%
“…Classical models can also be employed in this context, like those based on neuro-fuzzy systems [26,27], group method of data handling [28], and multilayer Perceptron [29]. In addition to prediction these approaches can be used for classification [30], through shallow layer structures [31][32][33] or deep learning strategies [34][35][36][37].…”
Section: Time Series Forecastingmentioning
confidence: 99%