电源技术2024，Vol.48Issue(6)：1154-1159,6.DOI:10.3969/j.issn.1002-087X.2024.06.028
基于VMD-SSA-HKELM的短期光伏功率预测
Short-term PV power prediction based on VMD-SSA-HKELM
摘要
Abstract
In order to improve the prediction accuracy of short-term photovoltaic power,a short-term photovoltaic power prediction model was presented,which combined variational mode decomposition and hybrid kernel extreme learning machine optimized by sparrow search algorithm.Pearson corre-lation coefficient was used to select the meteorological factors strongly correlated with photovoltaic power as the input variables of the forecast model.The square Euclidean distance was used as the ba-sis to measure the sample similarity,and the optimal training samples under different weather types were selected.In order to reduce the non-stationary of the data,VMD was used to decompose the original photovoltaic power data into a series of modal components with different bandwidths,and the HKELM models were established for each modal component.SSA algorithm was introduced to optimize the parameters of the HKELM model.The predicted results of each mode component were summed and reconstructed,and the predicted results of photovoltaic power were obtained.The simu-lation results show that the proposed model has higher prediction accuracy than BPNN,ELM,VMD-KELM and VMD-HKELM models,which verifies the accuracy and effectiveness of the proposed model.关键词
光伏功率预测/混合核极限学习机/变分模态分解/麻雀搜索算法Key words
photovoltaic power prediction/hybrid kernel extreme learning machine/variational mode decomposition/sparrow search algorithm分类
信息技术与安全科学引用本文复制引用
杨荔强,崔双喜..基于VMD-SSA-HKELM的短期光伏功率预测[J].电源技术,2024,48(6):1154-1159,6.基金项目
国家自然科学基金(52067020) （52067020）
