Wind Power Prediction Based on SSA-SVM

Aiming at the problem that the wind power prediction accuracy is not high due to wind volatility and randomness, a prediction model based on sparrow search algorithm (SSA) and support vector machine (SVM) was designed. Firstly, the method based on Thompson tau and quartile was used to identify and process the abnormal data of wind speed and wind power. Then, SSA was used to optimize the penalty coefficient and the kernel parameter of SVM, and SSA-SVM prediction model was constructed. Through the experimental simulation analysis of the measured data from a wind farm in China, it is proved that SSA-SVM prediction model is effective, and the prediction accuracy of the proposed model is improved compared with the prediction model based on SVM.