摘要
为提高光伏功率预测精确度,提出一种基于经验模态分解(Empirical Mode Decomposition,EMD)-天鹰优化器(Aquila Optimizer,AO)-深度极限学习机(Deep Extreme Learning Machine,DELM)的组合光伏功率预测模型.该算法对光伏发电影响因素进行分析筛选,选出与光伏输出功率高度相关的因素作为输入变量,并采用经验模态分解(EMD)将光伏原始功率数据分解为多个特征模态函数(Intrinsic Mode Function,IMF).然后,将分解得到的IMF分量分别输入DELM预测模型,同时通过AO优化算法对DELM初始输入权重进行优化,从而提高深度极限学习机的泛化能力.最后,将各IMF分量预测结果叠加求和得到最终预测结果.通过仿真结果表明,本文提出的EMD-AO-DELM预测模型,相较于单一DELM模型具有更好的预测精度,证明了所提方法的有效性.
To improve the accuracy of PV power prediction,this paper proposes a combined PV power prediction model based on Empirical Mode Decomposition(EMD)-Aquila Optimizer(AO)-Deep Extreme Learning Machine(DELM).The algorithm analyzes and filters the factors influencing PV power generation,selects the factors that are highly correlated with PV output power as input,and decomposes the PV raw power data into multiple eigenmode functions(IMF)by using empirical mode decomposition(EMD).Then the decomposed IMF components are input into the DELM prediction model separately,while the initial input weights of DELM are optimized by the AO optimization algorithm,so as to improve the generalization ability of the deep limit learning machine.Finally,the prediction results of each of the IMF components are superimposed and summed up to obtain the final prediction results.The simulation results show that the EMD-AO-DELM prediction model proposed in this paper has better prediction accuracy than the single DELM model,which proves the effectiveness of the proposed method.
作者
曹哲
赵葵银
王田宇
黄玮杰
司孟娇
林国汉
CAO Zhe;ZHAO Kuiyin;WANG Tianyu;HUANG Weijie;SI Mengjiao;LIN Guohan(College of Electrical and Information Engineering,Hunan Institute of Engineering,Xiangtan 411104,China)
出处
《湖南工程学院学报（自然科学版）》
2023年第4期6-14,共9页
Journal of Hunan Institute of Engineering(Natural Science Edition)
基金
湖南省科技创新计划重点项目(2020RC5019)
湖南省自然科学基金项目(2022JJ50122).
关键词
光伏发电
预测算法
经验模态分解
深度极限学习机
photovoltaic power generation
prediction algorithm
empirical mode decomposition
deep extreme learning machine
