In order to improve the accuracy of wind power prediction and ensure the effective utilization of wind energy, a short-term wind power prediction model based on variational mode decomposition (VMD) and an extreme learning machine (ELM) optimized by an improved grey wolf optimization (GWO) algorithm is proposed. The original wind power sequence is decomposed into series of modal components with different center frequencies by the VMD method and some new sequences are obtained by phase space reconstruction (PSR). Then, the ELM model is established for different new time series, and the improved GWO algorithm is used to optimize its parameters. Finally, the output results are weighted and merged as the final predicted value of wind power. The root-mean-square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of the proposed VMD-improved GWO-ELM prediction model in the paper are 5.9113%, 4.6219%, and 13.01% respectively, which are better than these of ELM, back propagation (BP), and the improved GWO-ELM model. The simulation results show that the proposed model has higher prediction accuracy than other models in short-term wind power prediction.
When basic particle swarm optimization algorithm (PSO) is used to resolve some complex problems, its global optimal model usually falls into local optimal value and its local model has slowest convergence velocity in the later stage of evolution. So, a simplified particle swarm optimization algorithm is proposed. Firstly, all particles in whole swarm are divided into three categories, denoted as the better particles, the ordinary particles and the worse particles according to their fitness. After the velocity equation of PSO is analyzed, the velocity part of PSO's iteration equations is removed rationally. Then, these three types of particles evolve dynamically according to three corresponding kinds of simplified algorithm models. Then, PSO, other two improved PSOs with good optimization performance at present and simplified PSO proposed by this paper all are used to resolve the optimization problems of four widely used test functions, and the results show that simplified PSO has better optimization performance than others.
In this paper, a short-term wind speed prediction model, called CEEMDAN-SE-Improved PIO-GRNN, is proposed to optimize the accuracy of the short-term wind speed forecast. This model is established on account of the optimized General Regression Neural Network (GRNN) method optimized by three algorithms, which are Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Sample Entropy (SE), and Pigeon Inspired Optimization (PIO), separately. Firstly, decomposing the original wind speed sequences into several subsequences with different complexity by CEEMDAN. Then, the complexity of each subsequence is judged by SE and the similar subsequences are combined into a new sequence to reduce the scale of calculation. Afterwards, the GRNN model optimized by improved PIO is used to predict each new sequence. Finally, the predicted results are superposed as the eventual predicted value. Implementing the prediction for the wind speed data of a wind field in north China within 30 days by applying the different prediction models, namely, GRNN, CEEMDAN-GRNN, Improved PIO-GRNN, and CEEMDAN-SE-Improved PIO-GRNN which are proposed in this paper. Comparing the prediction curves of different models with the fitting curve of the actual wind speed shows that the optimal fitting effect and minimum error value are included in CEEMDAN-SE-Improved PIO-GRNN model. Specifically, the values of mean squared error (MSE), mean absolute error (MAE) and weighted mean absolute percentage error (WMAPE) separately decrease by 0.6222, 0.3334, and 8.5766%, which compare with the single prediction model GRNN. Meanwhile, diebold-mariano (DM) test shows that the prediction ability of the two models is significantly different. The above statements indicate the proposed model does great advance in the precision of short-term wind speed prediction.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.