Optimization of short-term wind power prediction of Multi-kernel Extreme Learning Machine based on Sparrow Search Algorithm

Aiming at the problem that the single kernel function of kernel extreme learning machine (KELM) cannot adapt to the variable actual wind power. This paper proposes a modified prediction model which can increase the accuracy of prediction. The prediction model uses multiple kernel functions instead o...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of physics. Conference series Ročník 2527; číslo 1; s. 12075 - 12079
Hlavní autoři: Wang, Fan, Gao, Guige
Médium: Journal Article
Jazyk:angličtina
Vydáno: Bristol IOP Publishing 01.06.2023
Témata:
Accuracy
Artificial neural networks
Kernel functions
Machine learning
Optimization
Physics
Prediction models
Search algorithms
Wind power
ISSN:1742-6588, 1742-6596
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Aiming at the problem that the single kernel function of kernel extreme learning machine (KELM) cannot adapt to the variable actual wind power. This paper proposes a modified prediction model which can increase the accuracy of prediction. The prediction model uses multiple kernel functions instead of a single kernel function and optimizes the kernel parameters by using a sparrow search algorithm (SSA). Finally, through the simulation and comparison experiments, the proposed prediction model has better prediction accuracy than the conventional prediction model.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2527/1/012075