Forecasting wind speed using support vector regression and feature selection

Botha, Nicolene; Walt, Christiaan M Van der

doi:10.1109/robomech.2017.8261144

Cited by 6 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To fully evaluate the proposed model, a comparison is made with the following models; Group Method of Data Handling Neural Network (GMDHNN) [27], Regression Neural Network (GRNN) [28], Regression Trees (RTs) [29], Relevance Vector Machine (RVM) [30], and Support Vector Regression (SVR) [31]. Tables 3 and 4 present the scores of GMDHNN, GRNN and RTs, RVM and SVR, respectively, on the error metrics, for the 1-min-ahead predictions.…”

Section: Comparison With Other Forecasting Modelsmentioning

confidence: 99%

A Data-Driven Short-Term Forecasting Model for Offshore Wind Speed Prediction Based on Computational Intelligence

2019

View full text Add to dashboard Cite

Wind speed forecasting is an important element for the further development of offshore wind turbines. Due to its importance, many researchers have proposed different models for wind speed forecasting that differ in terms of the time-horizon of the forecast, types and number of inputs, complexity, structure, and others. Wind speed series present high nonlinearity and volatilities, and thus an effective model should successfully deal with those features. An approach to deal with the nonlinearities and volatilities is to utilize a time series processing technique such as the wavelet transform. In the present paper, an ensemble data-driven short-term wind speed forecasting model is developed, tested and applied. The term “ensemble” refers to the combination of two different predictors that run in parallel and the prediction is obtained by the predictor that leads to the lowest error. The proposed model utilizes the wavelet transform and is compared with other models that have been presented in the related literature and outperforms their accuracy. The proposed forecasting model can be used effectively for 1 min and 10 min ahead horizon wind speed predictions.

show abstract

Section: Comparison With Other Forecasting Modelsmentioning

confidence: 99%

A Data-Driven Short-Term Forecasting Model for Offshore Wind Speed Prediction Based on Computational Intelligence

2019

View full text Add to dashboard Cite

show abstract

“…Wind power is the most attractive renewable energy technology due to its high efficiency and low pollution level. However, because the power generated by the Wind Energy Conversion System (WECS) varies with atmospheric weather and wind speed, unexpected fluctuations in WECS power generation increase the operating cost of the power system by increasing the need for primary reserves, it can increase and pose a potential risk to power reliability [1].…”

Section: Introductionmentioning

confidence: 99%

“…In addition, wind forecasts are used for traditional power plant event planning and spot market electricity trading. [1] Although the prediction accuracy of wind power forecasting is lower than the prediction accuracy of load forecasting, wind forecasts still play a key role in addressing operational challenges in electricity supply. Recently, several methods have been employed the wind forecasting.…”

Section: Introductionmentioning

confidence: 99%

Support Vector Regression Approach for Wind Forecasting

Yamin

Giyats²

2022

ijasce

View full text Add to dashboard Cite

The government policies to fully support the G20 sustainability emphasize increased use of renewable energy. The high penetration of wind energy into power systems poses many challenges for energy system operators, primarily due to the unpredictability and variability of wind energy production. Wind power may not be provided, but accurate forecasting of wind speed and power generation helps grid operators reduce the risk of reduced electricity reliability. Accurately predicting wind speeds over 1 to 24 hours based on these conditions is important for predicting potential energy supply. These short-term forecasts are important to support wind power planning, so the required base load supply for the grid is always guaranteed (even if the wind power output fluctuates significantly). This task demonstrates that the relative forecasting performance of a support vector regression (SVR) wind forecasting system can be improved by systematically selecting and combining related input functions that affect wind speed. Shows the results of data collected in Sidrap, Indonesia, during the six months of 2019. This paper explained key methods of wind forecasting, based on the evaluation of wind speeds and wind speed prediction methods. The RMSE from the SVR shows an 8% - 9% improvement on the RMSE of the persistence forecast every 1 hour. Wind speed estimation using a support vector regression approach has the potential for further development, one of which is determining the potential location of wind-based renewable sources and Wind Energy Conversion System (WECS) can make more efficient.

show abstract

“…Niu et al (2018) presented a multi-step wind speed forecasting model using optimal FS, modified bat algorithm and cognition strategy. Botha & Walt (2017) combined FS with SVM to predict short-term wind speed. Kong et al (2015) combined feature selection and reduced support vector machines (RSVM) for wind speed forecasting.…”

Section: Introductionmentioning

confidence: 99%

A combined model for short-term wind speed forecasting based on empirical mode decomposition, feature selection, support vector regression and cross-validated lasso

Wang

2021

PeerJ Computer Science

View full text Add to dashboard Cite

Background The planning and control of wind power production rely heavily on short-term wind speed forecasting. Due to the non-linearity and non-stationarity of wind, it is difficult to carry out accurate modeling and prediction through traditional wind speed forecasting models. Methods In the paper, we combine empirical mode decomposition (EMD), feature selection (FS), support vector regression (SVR) and cross-validated lasso (LassoCV) to develop a new wind speed forecasting model, aiming to improve the prediction performance of wind speed. EMD is used to extract the intrinsic mode functions (IMFs) from the original wind speed time series to eliminate the non-stationarity in the time series. FS and SVR are combined to predict the high-frequency IMF obtained by EMD. LassoCV is used to complete the prediction of low-frequency IMF and trend. Results Data collected from two wind stations in Michigan, USA are adopted to test the proposed combined model. Experimental results show that in multi-step wind speed forecasting, compared with the classic individual and traditional EMD-based combined models, the proposed model has better prediction performance. Conclusions Through the proposed combined model, the wind speed forecast can be effectively improved.

show abstract

Forecasting wind speed using support vector regression and feature selection

Cited by 6 publications

References 15 publications

A Data-Driven Short-Term Forecasting Model for Offshore Wind Speed Prediction Based on Computational Intelligence

A Data-Driven Short-Term Forecasting Model for Offshore Wind Speed Prediction Based on Computational Intelligence

Support Vector Regression Approach for Wind Forecasting

A combined model for short-term wind speed forecasting based on empirical mode decomposition, feature selection, support vector regression and cross-validated lasso

Contact Info

Product

Resources

About