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

Abstract

a b s t r a c tIn 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, M exico, 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 (5e23 h ahead) short term WSF and WPF than those made with persistence and autoregressive models.

Numerical weather prediction wind correction methods and its impact on computational fluid dynamics based wind power forecasting

“…The ratio between training and testing samples could be different under various wind farms, especially for complex terrain, the correction results will be sensitive to input wind conditions. Based on the experience 32,33 and simple sensitivity analysis against the proportion of training and testing samples, a ratio of 2:1 is selected in this case. The first twenty days in a month are taken as training samples to establish the three correction models, and the last ten days are taken as testing samples to validate the correction effects of each model.…”

Zaman Serisi Analiz Metotları Kullanılarak Rüzgâr Hızının Tahmin Edilmesi

“…Zuluaga et al [10] presented short-term wind speed prediction based on robust Kalman filtering. Based on support vector regression, a hybrid methodology for wind speed forecasting was presented by Santamaria-Bonfil et al [11]. They used wind speed data from the Mexican Wind Energy Technology Center to evaluate their method.…”

“…Moving average method, exponential smoothing method, exponential smoothing with trend method, and exponential smoothing with trend and seasonality method was used for forecasting. To evaluate the models' performance, mean error (ME), mean absolute error (MAE) [11,[19][20], mean square error (MSE), mean absolute percentage error (MAPE) [8,17] and root mean square error (RMSE) [8,11,[19][20] statistics were calculated. The low performance measure values seen in results indicate that the methods used in this study can be forecast for wind speed.…”

Previsões Pontuais E Intervalares De Séries Temporais De Alta Frequência Com Sistema De Lógica Fuzzy

“…As regras fuzzy SE-ENTÃO do tipo Mamdani podem ser interpretadas como relações fuzzy de implicação 10 [18], com função de pertinência → ( , ) ∈ [0,1] da forma apresentada na equação (3.3). Esta função de pertinência mede o "grau de verdade" da relação de implicação fuzzy entre (entrada, antecedente) e (saída, consequente).…”

“…Estes podem ser classificados em, basicamente, quatro categorias: modelos estatísticos (que podem ser subdivididos em modelos de estatística clássica [1,3] e de estatística bayesiana [4,5]), modelos de inteligência computacional (que podem ser subdivididos em modelos de lógica fuzzy [6,7], de redes neurais [8,9], de support vector regression [10,11] e outros), modelos híbridos (que combinam diferentes modelos, e.g. [12,13]), e outros tipos de modelos (e.g.…”