[1]林兴宇,肖迎群,张 苏.基于极限学习机分位回归的光伏出力区间预测方法[J].机械与电子,2023,41(06):3-9.
　LIN Xingyu,XIAO Yingqun,ZHANG Su.PV Output Interval Forecasting Method Based on QRELM Algorithm[J].Machinery & Electronics,2023,41(06):3-9.
点击复制

基于极限学习机分位回归的光伏出力区间预测方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
41
期数:
2023年06期
页码:
3-9
栏目:
设计与研究
出版日期:
2023-06-25

文章信息/Info

Title:
PV Output Interval Forecasting Method Based on QRELM Algorithm
文章编号:
1001-2257 ( 2023 ) 06-0003-07
作者:
林兴宇 1 ; 肖迎群 1 ; 张 苏 2
1. 贵州大学电气工程学院,贵州 贵阳 550025 ; 2. 贵州理工学院大数据学院,贵州 贵阳 550003
Author(s):
LIN Xingyu1 ;  XIAO Yingqun1 ;  ZHANG Su2
( 1.College of Electrical Engineering , Guizhou University , Guiyang 550025 , China ; 2.College of Big Data , Guizhou Institute of Technology , Guiyang 550003 , China)
关键词:
太阳能; 预测; 主成分分析; 分位数回归; 极限学习机
Keywords:
solar energy ;  forecasting ;  principal component analysis ;  quantile regression ;  ELM
分类号:
TM615
文献标志码:
A
摘要:
提出一种基于极限学习机分位数回归算法( QRELM )并考虑季节特性的短期光伏出力区间预测模型。首先以光伏出力与经过主成分分析( PCA )降维的气象因子组成 QRELM 输入样本,学习内在规律并生成不同分位水平分位数;进一步以综合评价指标为目标函数,使用改进的差分进化算法( DE )对不同分位数线性加权组合得到预测区间上下界,实现对光伏出力区间的单步超前预测。实验证明,相比传统神经网络算法,分季节训练 QRELM 模型、 PCA 与 DE 组合算法可以有效提高预测区间性能。
Abstract:
A short-term PV output interval prediction model based on extreme learning machine quantile regression algorithm( QRELM ) is proposed.Firstly , the QRELM input samples were composed of PV output and meteorological factors reduced by principal component analysis( PCA ) to solve the quantiles of different quantile levels.Further , with the comprehensive evaluation index as the objective function , the improved differential evolution algorithm( DE ) was used for quantile linear weighted combination to obtain the upper and lower bounds of the prediction interval , so as to realize the one-step-ahead forecasting of PV output interval.Experiments show that compared with the traditional neural network algorithm , seasonal classification , PCA and DE combined algorithm can effectively improve the prediction interval performance.

参考文献/References:

[ 1 ] LI B H , ZHANG J.A review on the integration of probabilistic solar forecasting in power systems[ J ] . Solar energy , 2020 , 210 : 68-86.

[ 2 ] 马磊,黄伟,李克成,等 . 基于 Attention-LSTM 的光伏超短期功率预测 模型[ J ] . 电 测与 仪表, 2021 , 58( 2 ): 146-152.
[ 3 ] 陈禹帆,温蜜,张凯,等 . 基于相似日匹配及 TCN-Attention 的短期光伏出力预测[ J ] . 电测与仪表, 2022 ,59 ( 10 ): 108-116.
[ 4 ] 杨茂,王凯旋 . 基于 CEEMD-DBN 模型的光伏出力日前区间预测[ J ] . 高电压技术, 2021 , 47 ( 4 ): 1156-1164.
[ 5 ] MA M , HE B , SHEN R J , et al.An adaptive interval power forecasting method for photovoltaic plant and its optimization[ J ] .Sustainable energy technologies and assessments , 2022 , 52 : 102360.
[ 6 ] HAN Y T , WANG N B , MA M , et al.A PV power interval forecasting based on seasonal model and nonparametric estimation algorithm [ J ] .Solar energy , 2019 , 184 : 515-526.
[ 7 ] 涂智福,丁坚勇,周凯 . 基于 VMD 和 GP 的短期风电功率置信区间预测[ J ] . 电测与仪表, 2020 , 57 ( 1 ): 84-88.
[ 8 ] 杨锡运,邢国通,马雪,等 . 一种核极限学习机分位数回归模型及风电功率区间预测[ J ] . 太阳能学报, 2020 , 41( 11 ): 300-306.
[ 9 ] 王晓东,鞠邦国,刘颖明,等 . 基于 QR-NFGLSTM 与核密度估计的风电功率概率预测[ J ] . 太阳能学报,2022 , 43 ( 2 ): 479-485.
[ 10 ] HU J M , TANG J W , LIN Y Y.A novel wind power probabilistic forecasting approach based on joint quantile regression and multi-objective optimization [ J ] . Renewable energy , 2020 , 149 : 141-164.
[ 11 ] NIU H H , YANG Y , ZENG L C , et al.ELM-QR based nonparametric probabilistic prediction method for wind power[ J ] .Energies , 2021 , 14 ( 3 ): 1-15.
[ 12 ] 王炳忠 . 太阳辐射计算 讲座 第三讲地外水平面辐射量的计算[ J ] . 太阳能, 1999 ( 4 ): 12-13.
[ 13 ] 韩立涛 . 考虑云遮挡的光伏超短期功率预测研究[ D ] .北京:华北电力大学,2018.
[ 14 ] HUANG G B , ZHOU H M , DING X J , et al.Extreme learning machine for regression and multiclass classi fication [ J ] .IEEE Transactions on systems , man , and cybernetics , part B( cybernetics ), 2011 , 42 ( 2 ): 513-529.
[ 15 ] 王昕,黄柯,郑益慧,等 . 基于 PNN / PCA / SS SVR 的光伏发电功率短期预测方法[ J ] . 电力系统自动化,2016 , 40 ( 17 ): 156-162.
[ 16 ] 万灿,崔文康,宋永华 . 新能源电力系统概率预测:基本概念与数学原理[ J ] . 中国电机工程学报, 2021 , 41( 19 ): 6493-6509.
[ 17 ] BRUNINX K , DELARUE E.A statistical description of the error on wind power forecasts for probabilistic reserve sizing [ J ] .IEEE Transactions on sustainable energy , 2014 , 5 ( 3 ):995-1002.
[ 18 ] DAS S , SUGANTHAN P N.Differential evolution : a survey of the state-of-the-art [ J ] .IEEE Transactions on evolutionary computation , 2010 , 15 ( 1 ): 4-31.

相似文献/References:

[1]徐 立,元春波,徐 敏,等.基于粒子群卷积算法的转杆机械损伤预测研究[J].机械与电子,2024,42(10):76.
　XU Li,YUAN Chunbo,XU Min,et al.Study on Prediction of Rod Mechanical Damage Based on Particle Population Convolution Algorithm[J].Machinery & Electronics,2024,42(06):76.

备注/Memo

备注/Memo:
收稿日期: 2022-12-28
基金项目:贵州省科技支撑项目(黔科合支撑[ 2021 ]一般365 )
作者简介:林兴宇 ( 1997- ),男,贵州贵阳人,硕士研究生,研究方向为光伏出力区间预测;肖迎群 ( 1975- ),男,湖南邵阳人,博士,副教授,研究方向为高维数据分析、机器学习。
更新日期/Last Update: 2023-06-26