Wind power prediction based on multiple support vector machines

Wind power forecasting is of great significance in grid dispatching. This paper proposes a statistical model based on feature classification least squares support vector machine, which can predict short-term wind power. First of all, this paper analyzes the data of an actual power plant. After analyzing the data, it is found that there is uncertainty in the existence of multiple powers at the same wind speed. Then, in order to resolve this uncertainty, the wind speed and wind speed trend samples are density clustered according to the DBSCAN method. The clustering results are divided into several categories, and the samples of different categories are modeled by least squares support vector machines. Finally, the effectiveness of the proposed prediction model is compared with that of unclassified samples through the prediction model. Simulation results show that the designed model has higher prediction power accuracy.