A Hybrid Structure Based on VMD-LSSVM and Improved Quantum Particle Swarm Simultaneous Optimization for Wind Speed Prediction

To enhance the forecasting performance, a novel short-term wind speed prediction model based on the improved quantum particle swarm optimization algorithm (IQPSO) for synchronous optimization of variational mode decomposition (VMD) and least squares support vector machine (LSSVM) is proposed. In the proposed model, IQPSO is used to optimize the internal parameters including decomposition layers and penalty factors of VMD and the kernel parameters of LSSVM. The typical statistical indicators including mean absolute error (MAE), root mean square error (RMSE) and correlation coefficient (R2) are utilized to evaluate the prediction model. The experimental results show that the statistical indicators RMSE, RMSE and R2 of the improved quantum particle swarm simultaneous optimization VMD-LSSVM model are only 0.62 m/s, 0.47 m/s, and 0.95, which have relatively high accuracy compared with the rest of the prediction models.