Application of WOA-Based LSSVM Model for Wind Speed Prediction in Mianyang, China

Abstract

In recent years, countries have vigorously developed renewable energy resources to alleviate energy shortages and improve the environment. Wind energy, as a clean and renewable new energy source, has been increasing its power generation capacity, but the wind power generation itself has the characteristics of volatility and instability which makes wind power generation more difficult. Therefore, a novel prediction model based on the least squares support vector machine (LSSVM) with whale optimization algorithm (WOA) is proposed in the paper to improve the prediction accuracy and applied to the wind speed prediction in Mianyang. The model is implemented in python language, and then the prediction results are then evaluated quantitatively using the mean absolute percentage error (MAPE), and the results of the proposed model are compared with models such as eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR) and Random Forest (RF). Further, the MAPE of the prediction results of the proposed model is about 4.7%-5.5%, which can be 6.3% higher than other models at best. The results show that the proposed prediction model can have good prediction accuracy and generalization performance and can be applied to other fields in the future.