Short-term Wind Speed Forecasting Based on Singular Spectrum Analysis, Fuzzy C-Means Clustering, and Improved POABP

To enhance the wind speed prediction precision, we propose a hybrid prediction model based on singular spectrum analysis (SSA), fuzzy c-mean clustering (FCM), and an improved pelican optimization algorithm (IPOA-BP). First, the original wind speed signal is denoised by SSA; second, classifying BP input data using FCM, and the classification counts of two different data sets are obtained by multiple experiments; third, the improved pelican optimization algorithm (IPOA) is used to optimize the weights and thresholds. The final experimental results show that the model proposed in this paper has higher prediction accuracy compared with the other five models.