Short-term Wind Speed Prediction Based On Quadratic Decomposition Improved Particle Swarm Optimization Extreme Learning Machine

An empirical mode decomposition (EMD)-variational mode decomposition (VMD) quadratic decomposition, particle swarm optimization (PSO)-extreme learning machine (ELM) based short-term wind speed prediction model is proposed. EMD is first used to decompose the non-stationary series into multiple intrinsic mode functions (IMFs). The complexity of each mode component is measured using the sample entropy (SE), the high frequency subsequence is decomposed again using VMD. The PSO-ELM prediction is performed separately for each high frequency sequence after the secondary decomposition and the original low frequency sequence, the predicted value of the sum component is added at last. By predicting the U.S. national wind power plant data, the experimental results prove that the model constructed in this paper has a better prediction effect compared with other models, further improves the prediction accuracy.