Nowadays, wind power andprecise forecasting are of great importancefor the development ofmodern electricalgrids.In this paperwepropose aprediction systemfor time seriesbased onKernelPrincipalComponent Analysis(KPCA) andExtremeLearningMachine(ELM). To compare the proposed approach, threedimensionality reduction techniques were used:full space (50 variables), part of space (last four variables) and classical Principal Components Analysis (PCA). These models were compared using three evaluation criteria: mean absoluteerror (MAE), root mean squareerror (RMSE), and normalizedmean square error (NMSE). The results show that the reduction of the original input space affectspositively the prediction output of the wind speed.Thus,It can be concluded that the non linear model (KPCA)model outperform the other reduction techniques in terms of prediction performance.