A novel wind speed prediction method based on support vector machine optimized by genetic algorithm

Abstract: Wind energy is attracting more and more attention nowadays, because of the renewable, nonpolluting characteristics. Accurate wind speed prediction can provide necessary technical support and guidance in the application of wind power in the electricity grid. In order to improve the accuracy of wind speed prediction, a combination genetic algorithm and support vector machine (SVM) model has been proposed to forecast wind speed. Firstly, grey model was adopted to accumulate the original wind speed data and weaken the randomness of data sequence, and then SVM model is used to predict the wind speed. Furthermore, using the regressive features of grey model to reduce the prediction results and obtain the final predicted value of wind speed. The comparison results with other popular predicting algorithms, BP and standard SVM, show that, the GA-SVM model can improve the forecasting accuracy of short term wind speed and is of a certain practical value.