Probabilistic Stacked Denoising Autoencoder for Power System Transient Stability Prediction With Wind Farms

To address the uncertainties of renewable energy and loads in transient stability assessment with credible contingencies, this letter proposes a stacked denoising autoencoder (SDAE)-based probabilistic prediction method. The correlations among wind farms have been effectively considered through the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on power systems Ročník 36; číslo 4; s. 3786 - 3789
Hlavní autoři: Su, Tong, Liu, Youbo, Zhao, Junbo, Liu, Junyong
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 01.07.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Confidence intervals
Monte Carlo simulation
Noise reduction
Power system stability
Probabilistic logic
probabilistic prediction
Stability analysis
Stability criteria
stacked denoising autoencoder (SDAE)
Statistical analysis
Transient analysis
Transient stability
Wind farms
Wind power
Wind power generation
wind uncertainty
ISSN:0885-8950, 1558-0679
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:To address the uncertainties of renewable energy and loads in transient stability assessment with credible contingencies, this letter proposes a stacked denoising autoencoder (SDAE)-based probabilistic prediction method. The correlations among wind farms have been effectively considered through the variable transformation via the Cholesky decomposition. SDAE allows learning the mapping relationship between operational features and the transient stability margin. The possible operation scenarios are sampled under different confidence levels to generate appropriate inputs for SDAE to assess the probabilistic transient stability distribution. Results on the modified IEEE 39-bus system show that our proposed method can achieve a similar level of accuracy as the benchmark and improved Monte Carlo simulations-based methods while having much higher computational efficiency.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0885-8950
1558-0679
DOI:10.1109/TPWRS.2020.3043620