Research on Short-term Wind Power Prediction Based on AdaBoost-PSO-ELM Model
For the uncertainty and volatility of wind power and the weaker generalization ability of the current wind power pre-diction models,a short-term wind power prediction model based on AdaBoost-PSO-ELM is proposed.Particle swarm optimiza-tion(PSO)algorithm is used to optimize the input weights and initial thresholds of the extreme learning machine(ELM).Combined with adaptive boosting(AdaBoost)algorithm,each weak predictor(PSO-ELM model)is weighted and fused into a wind power prediction model,and the prediction results are output.The prediction model is verified by the actual measurement data.The prediction indicators are compared with the current wind power prediction methods.The results show that the Ada-Boost-PSO-ELM model has higher prediction accuracy and better generalization ability.
万方数据
维普
