Wind speed forecasting for wind farms: A method based on support vector regression

In this paper, a hybrid methodology based on Support Vector Regression for wind speed forecasting is proposed. Using the autoregressive model called Time Delay Coordinates, feature selection is performed by the Phase Space Reconstruction procedure. Then, a Support Vector Regression model is trained...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Renewable energy Ročník 85; s. 790 - 809
Hlavní autoři: Santamaría-Bonfil, G., Reyes-Ballesteros, A., Gershenson, C.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.01.2016
Témata:
algorithms
Genetic algorithms
methodology
Mexico
Non-linear analysis
Phase space reconstruction
regression analysis
Support vector regression
time series analysis
wind farms
wind power
wind speed
Wind speed forecasting
Mexico
Support vector regression
Phase space reconstruction
Non-linear analysis
Wind speed forecasting
Genetic algorithms
ISSN:0960-1481, 1879-0682
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, a hybrid methodology based on Support Vector Regression for wind speed forecasting is proposed. Using the autoregressive model called Time Delay Coordinates, feature selection is performed by the Phase Space Reconstruction procedure. Then, a Support Vector Regression model is trained using univariate wind speed time series. Parameters of Support Vector Regression are tuned by a genetic algorithm. The proposed method is compared against the persistence model, and autoregressive models (AR, ARMA, and ARIMA) tuned by Akaike's Information Criterion and Ordinary Least Squares method. The stationary transformation of time series is also evaluated for the proposed method. Using historical wind speed data from the Mexican Wind Energy Technology Center (CERTE) located at La Ventosa, Oaxaca, México, the accuracy of the proposed forecasting method is evaluated for a whole range of short termforecasting horizons (from 1 to 24 h ahead). Results show that, forecasts made with our method are more accurate for medium (5–23 h ahead) short term WSF and WPF than those made with persistence and autoregressive models. •Short-term wind speed forecasting was performed using non-linear and machine learning methods.•Univariate wind data was mapped to a higher dimensional space by the phase space reconstruction procedure.•SVR and a genetic algorithm estimates a representative function of site's wind speed using the mapped data.•Lyapunov exponents and complexity measures revealed that data presents features of a chaotic processes.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0960-1481
1879-0682
DOI:10.1016/j.renene.2015.07.004