Short-term Prediction of Wind and Photovoltaic Power Based on the Fusion of Attention Mechanism and Improved Whale Optimization Algorithm

With the aim of enhancing the accuracy of predictions and stability of wind and solar power generation prediction models in different scenarios, a deep learning hybrid prediction model integrating the attention mechanism and the improved whale optimization algorithm is proposed. Firstly, Pearson cor...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 3135; číslo 1; s. 12021 - 12026
Hlavní autoři: Zou, Jin, Ye, Jiaqing, Xue, Zhiliang, Zhang, Li, Wu, Feiyun
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.11.2025
Témata:
Accuracy
Algorithms
Correlation analysis
Improve the whale optimization algorithm
Long short-term memory Attention mechanism
Luminous intensity
Optimization
Optimization algorithms
Pearson correlation
Photovoltaic and wind power short-term forecasting
Prediction models
Solar energy
Solar power generation
Wind speed
ISSN:1742-6588, 1742-6596, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:With the aim of enhancing the accuracy of predictions and stability of wind and solar power generation prediction models in different scenarios, a deep learning hybrid prediction model integrating the attention mechanism and the improved whale optimization algorithm is proposed. Firstly, Pearson correlation analysis is employed to measure the association between each feature and wind and solar power in order to select the meteorological features with stronger correlation. Secondly, given the limitations of traditional long short-term memory (LSTM) and Gate Recurrent Unit (GRU) models in power prediction, the LSTM-GRU hybrid prediction model is adopted for accurate short-term power prediction of wind and solar power. Then, a hybrid prediction model integrating the Attention mechanism (Attention) and the improved whale algorithm (IWOA) is put forward to enhance accuracy of wind and solar energy forecasts; Finally, the historical data of a certain new energy base in northwest China was taken as the experimental data, and the Attention-IWOA-LSTM-GRU model was used for prediction. The outcomes of the simulation indicate that, compared with the prediction effects of other models in the circumstances involving abrupt fluctuations in wind velocity and light intensity, the prediction accuracy of the Attention-IWOA-LSTM-GRU model is higher.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
1742-6596
DOI:10.1088/1742-6596/3135/1/012021