Locally recurrent neural networks for long-term wind speed and power prediction

The paper deals with a real-world application, the long-term wind speed and power forecasting in a wind farm using locally recurrent multilayer networks as forecast models. To cope with the complexity of the process and to improve the performance of the models, a class of optimal on-line learning al...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neurocomputing (Amsterdam) Ročník 69; číslo 4; s. 466 - 496
Hlavní autoři: Barbounis, T.G., Theocharis, J.B.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 2006
Témata:
Local learning algorithms
Local recurrent neural networks
Long-term wind forecasting
Recursive prediction error algorithm
Sensitivity networks
Recursive prediction error algorithm
Sensitivity networks
Local learning algorithms
Long-term wind forecasting
Local recurrent neural networks
ISSN:0925-2312, 1872-8286
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The paper deals with a real-world application, the long-term wind speed and power forecasting in a wind farm using locally recurrent multilayer networks as forecast models. To cope with the complexity of the process and to improve the performance of the models, a class of optimal on-line learning algorithms is employed for training the locally recurrent networks based on the recursive prediction error (RPE) algorithm. A global RPE algorithm is devised and three local learning algorithms are suggested by partitioning the GRPE into a set of sub-problems at the neuron level to reduce computational complexity and storage requirements. Experimental results on the wind prediction problem demonstrate that the proposed algorithms exhibit enhanced performance, in terms of convergence speed and the accuracy of the attained solutions, compared to conventional gradient-based methods. Furthermore, it is shown that the suggested recurrent forecast models outperform the atmospheric and time-series models.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2005.02.003