Research on Wind Power Climbing Output Power Prediction System Based on ISMC-PSO

摘要

At present, wind farms all use a single power climbing prediction model, which has poor generalization ability and low prediction accuracy. In order to solve this problem this paper analyzes the support vector machine (SVM) and extreme learning machine two grade prediction model of the single power, through the weight for these two model selection, the establishment of a large wind power grade combination forecast model, the improved particle swarm optimization (PSO) algorithm was applied to combination the weight of two single prediction model in the prediction model of optimization, the weighting parameters were optimized by combining the advantages of two single prediction model, further improve the prediction precision of the power of climbing. Then the system is modeled and simulated, and the simulation results verify the validity of the prediction model.