基于AdaBoost-PSO-ELM模型的短期风电功率预测研究  

Research on Short-term Wind Power Prediction Based on AdaBoost-PSO-ELM Model

作　　者：海云桥 王书行 HAI Yunqiao;WANG Shuxing(Chifeng Power Supply Company of State Grid East Inner Mongolia Electric Power Co.,Ltd.,Chifeng 024000,China)

机构地区：[1]国网内蒙古东部电力有限公司赤峰供电公司,内蒙古赤峰024000

出　　处：《微型电脑应用》2024年第12期224-227,共4页Microcomputer Applications

摘　　要：针对风电功率的不确定性和波动性,以及当前风电功率预测模型泛化能力较弱的问题,提出一种基于AdaBoost-PSO-ELM的短期风电功率预测模型。利用粒子群优化(PSO)算法对极限学习机(ELM)的输入权重和初始阈值进行寻优,结合自适应提升(AdaBoost)算法,将每个弱预测器(PSO-ELM模型)加权融合成风电预测模型,输出预测结果。通过实际测量数据对预测模型进行验证,并将预测指标与当前风电功率预测方法进行比较。结果表明,AdaBoost-PSO-ELM模型具有更高的精度和更好的泛化能力。For the uncertainty and volatility of wind power and the weaker generalization ability of the current wind power prediction models,a short-term wind power prediction model based on AdaBoost-PSO-ELM is proposed.Particle swarm optimization(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 AdaBoost-PSO-ELM model has higher prediction accuracy and better generalization ability.

关 键 词：风电 功率预测 混合优化算法 AdaBoost-PSO-ELM模型 极限学习机 

分 类 号：TM614[电气工程—电力系统及自动化]