Ultra-short-term wind power prediction based on PVMD-ESMA-DELM

Abstract

The non-linearity and non-stationarity of wind power data have brought great challenges to the safe operation of the power system. It is particularly important to effectively improve the accuracy of ultra-short-term prediction of wind power. Therefore, we propose an ultra-short-term wind power prediction method that particle swarm optimization-variational mode decomposition (PVMD), enhanced slime mold algorithm (ESMA) for elite opposition-based learning strategy (EOBL) and deep extreme learning machine (DELM). First, the particle swarm optimization algorithm (PSO) is used to optimize the two core parameters of the variational mode decomposition (VMD) to obtain the PVMD algorithm. The PVMD is used to decompose the original wind power data into a series of stable sub-sequences, and the rolling time series is used to analyze the sub-sequences decomposed by PVMD. Then the DELM predictive model is established and the input weights (e) and thresholds (bc) in DELM are optimized through ESMA, and the EOBL is used to improve the diversity and population quality of the slime mold population, thereby improving the global optimization performance and convergence accuracy of the slime mold algorithm (SMA), and further improving the prediction accuracy of the DELM model. Finally, each subsequence is substituted into the DELM optimized by the elite opposition based learning-slime mold algorithm (ESMA-DELM), and the prediction components are superimposed to obtain the final prediction result. Comparing the effects of several different forecasting models with the evaluation of calculation examples proves the effectiveness of the PVMD-ESMA-DELM blended forecasting model proposed in this paper, and gives a new approach for ultra-short-term wind power prediction.