引用本文:陈晓科,陈奇芳,何婷,黄锦成.低成本微电网轻量化在线超短期光伏功率预测算法设计[J].控制理论与应用,2016,33(12):1658~1666.[点击复制]
CHEN Xiao-ke,CHEN Qi-fang,HE Ting,HUANG Jin-cheng.Design of simpli?ed online ultra-short term photovoltaic output forecasting algorithm for low cost microgrid[J].Control Theory and Technology,2016,33(12):1658~1666.[点击复制]
低成本微电网轻量化在线超短期光伏功率预测算法设计
Design of simpli?ed online ultra-short term photovoltaic output forecasting algorithm for low cost microgrid
摘要点击 2005  全文点击 2014  投稿时间：2016-05-10  修订日期：2016-12-09
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2016.60303
  2016,33(12):1658-1666
中文关键词  光伏功率预测  超短期  轻量化  核函数极限学习机
英文关键词  photovoltaic output forecasting  ultra-short term  simpli?ed  extreme learning machine with kernel
基金项目  
作者单位邮编
陈晓科 广东电网有限责任公司电力科学研究院 510080
陈奇芳 新能源电力系统国家重点实验室 
何婷* 华南理工大学电力学院
华南理工大学电力学院 		510640
黄锦成 广东智造能源科技研究有限公司 
中文摘要
      本文结合用户侧光伏微电网的实际工程需求, 研究了满足嵌入式应用需求的轻量化在线超短期光伏功率 预测算法. 采用了核函数极限学习机算法作为在线超短期光伏功率预测算法的核心, 通过使用特征序列代替传统 时间序列作为训练样本集, 实现了数据量的轻量化设计; 通过基于趋势加权相似度的训练样本精选,提高了算法精 度, 简化了计算量, 降低了算法计算时间. 通过嵌入式系统实验测试结果表明,本文提出的轻量化超短期光伏预测 算法在精度、计算时间和数据存储等方面都能满足嵌入式系统低成本应用的需求.
英文摘要
      Based on the engineering requirement of user side photovoltaic (PV) microgrid, a simpli?ed online short term PV output forecasting algorithm is studied for embedded system application. Extreme learning machine with kernel (ELM K) algorithm is adopted as the main part. The traditional time sequence of training dataset is replaced with charac- teristic sequence of history data, therefore, the amount of storage place of training data is reduced. Because of the optimal training dataset is selected from original training dataset by trend weighted similarity, the accuracy is improved, also the amount of calculation and runtime of forecasting algorithm is reduced. The test results of embedded system show that the performance of proposed online short term PV output forecasting algorithm on accuracy, runtime and storage occupation can satisfy the requirement of low cost embedded system application.