基于CNN-GRU-ISSA-XGBoost的短期光伏功率预测
作者:
中图分类号:

TM391;TM615

基金项目:

天津市自然科学基金重点项目(08JCZDJC18600);天津市教委重点基金项目(2006ZD32)


Short term photovoltaic power prediction based on CNN-GRU-ISSA-XGBoost
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    针对光伏功率随机性及波动性大,单一预测模型往往难以准确分析历史数据波动规律,从而导致预测精度不高的问题,提出一种基于卷积神经网络-门控循环单元(CNN-GRU)和改进麻雀搜索算法(ISSA)优化的极限梯度提升(XGBoost)模型的短期光伏功率预测组合模型.首先去除历史数据中的异常值并对其进行归一化处理,利用主成分分析法(PCA)进行特征选取,以便更好地识别影响光伏功率的关键因素.然后采用CNN网络提取数据的空间特征,再经过GRU网络提取时间特征,针对XGBoost模型手动配置参数困难、随机性大的问题,利用ISSA对模型超参数寻优.最后对两种方法预测的结果用误差倒数法减小误差的同时对权重进行更新,得到新的预测值,从而完成对光伏功率的预测.实验结果表明,所提出的CNN-GRU-ISSA-XGBoost组合模型具有更强的适应性和更高的精度.

    Abstract:

    The high randomness and volatility of photovoltaic (PV) power makes it difficult for single prediction models to accurately analyze the fluctuation patterns in historical data,resulting in low prediction accuracy.To address this issue,a combined model for short-term PV power prediction was proposed,which incorporated Convolutional Neural Network,Gated Recurrent Unit (CNN-GRU) and an Improved Sparrow Search Algorithm (ISSA) for optimizing the eXtreme Gradient Boosting (XGBoost) model.First,the historical data were normalized after outlier removal,and feature selection was carried out via Principal Component Analysis (PCA) so as to better identify the key factors affecting photovoltaic power.Then,the CNN and GRU networks were used to extract the spatial and temporal features of the data,respectively.To address the difficulty in manually configuring parameters and high randomness of the XGBoost model,ISSA was used to optimize the hyperparameters of the model.Finally,the reciprocal error method was used to reduce the error of the results predicted by the two methods (CNN-GRU and ISSA-XGBoost) while the weights were updated to obtain new predicted values to complete the prediction of photovoltaic power.The experimental results show that the proposed CNN-GRU-ISSA-XGBoost model has strong adaptability and high accuracy.

    参考文献
    [1] 王珊珊,吴霓,何嘉文,等.基于改进Stacking与误差修正的短期太阳辐照度预测[J].南京信息工程大学学报(自然科学版),2023,15(6):684-691 WANG Shanshan,WU Ni,HE Jiawen,et al.Short-term solar irradiance prediction based on improved Stacking and error correction[J].Journal of Nanjing University of Information Science & Technology (Natural Science Edition),2023,15(6):684-691
    [2] 柴闵康,夏飞,张浩,等.基于云图特征自识别的光伏超短期预测模型[J].电网技术,2021,45(3):1023-1035 CHAI Minkang,XIA Fei,ZHANG Hao,et al.Ultra-short-term prediction of self-identifying photovoltaic based on sky cloud chart[J].Power System Technology,2021,45(3):1023-1035
    [3] 胡乙丹,姜吉祥,董霞.基于结合聚类与SVM参数寻优的短期电力负荷预测方法[J].电力信息与通信技术,2022,20(5):54-60 HU Yidan,JIANG Jixiang,DONG Xia.A short-term power load forecasting method based on combining clustering and SVM parameter optimization[J].Electric Power Information and Communication Technology,2022,20(5):54-60
    [4] Ding S,Li R J,Tao Z.A novel adaptive discrete grey model with time-varying parameters for long-term photovoltaic power generation forecasting[J].Energy Conversion and Management,2021,227:113644
    [5] 韩祥民,刘晓波,刘敏,等.基于改进EEMD与GA-BP的谐振接地故障选线方法[J].智慧电力,2021,49(12):80-87 HAN Xiangmin,LIU Xiaobo,LIU Min,et al.Resonant grounding fault line selection method based on improved EEMD and GA-BP model[J].Smart Power,2021,49(12):80-87
    [6] 孙东磊,王艳,于一潇,等.基于BP神经网络的短期光伏集群功率区间预测[J].山东大学学报(工学版),2020,50(5):70-76 SUN Donglei,WANG Yan,YU Yixiao,et al.Interval prediction of short-term regional photovoltaic power based on BP neural network[J].Journal of Shandong University (Engineering Science),2020,50(5):70-76
    [7] 葛浩然,夏宇,邹文进,等.基于RF-XGBoost的光伏发电功率预测[J].电气自动化,2022,44(5):12-15 GE Haoran,XIA Yu,ZOU Wenjin,et al.Prediction of photovoltaic power generation based on RF-XGBoost[J].Electrical Automation,2022,44(5):12-15
    [8] Liu J,Sun H W,Chang P,et al.Research of photovoltaic power forecasting based on big data and mRMR feature reduction[C]//2018 IEEE Power & Energy Society General Meeting (PESGM).August 5-10,2018,Portland,OR,USA.IEEE,2018:1-5
    [9] He B,Ma R Z,Zhang W W,et al.An improved generating energy prediction method based on Bi-LSTM and attention mechanism[J].Electronics,2022,11(12):1885
    [10] 汤德清,朱武,侯林超.基于CNN-LSTM-XGBoost模型的超短期光伏功率预测[J].电源技术,2022,46(9):1048-1052 TANG Deqing,ZHU Wu,HOU Linchao.Ultra-short-term photovoltaic power prediction based on CNN-LSTM-XGBoost model[J].Chinese Journal of Power Sources,2022,46(9):1048-1052
    [11] Khortsriwong N,Boonraksa P,Boonraksa T,et al.Performance of deep learning techniques for forecasting PV power generation:a case study on a 1.5 MWp floating PV power plant[J].Energies,2023,16(5):2119
    [12] Qian N,Wang X S,Fu Y C,et al.Predicting heat transfer of oscillating heat pipes for machining processes based on extreme gradient boosting algorithm[J].Applied Thermal Engineering,2020,164:114521
    [13] Xue J K,Shen B.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science & Control Engineering,2020,8(1):22-34
    [14] Jensi R,Jiji G W.An enhanced particle swarm optimization with levy flight for global optimization[J].Applied Soft Computing,2016,43:248-261
    [15] 李杨,蓝茂蔚,赵国钦,等.基于PCA-PSO-LSSVM的电站锅炉效率预测模型研究[J].热力发电,2021,50(12):43-50 LI Yang,LAN Maowei,ZHAO Guoqin,et al.Study on prediction model of utility boiler efficiency based on PCA-PSO-LSSVM[J].Thermal Power Generation,2021,50(12):43-50
    [16] 邬程欢,贺民,龚明波,等.基于极限区间与改进PCA-SOM的电气运行参数对专变健康影响的量化评价方法[J].电力系统保护与控制,2021,49(17):101-108 WU Chenghuan,HE Min,GONG Mingbo,et al.Quantitative evaluation based on limit interval and improved PCA-SOM of electrical operating parameter health status of a special transformer[J].Power System Protection and Control,2021,49(17):101-108
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

岳有军,吴明沅,王红君,赵辉.基于CNN-GRU-ISSA-XGBoost的短期光伏功率预测[J].南京信息工程大学学报(自然科学版),2024,16(2):231-238
YUE Youjun, WU Mingyuan, WANG Hongjun, ZHAO Hui. Short term photovoltaic power prediction based on CNN-GRU-ISSA-XGBoost[J]. Journal of Nanjing University of Information Science & Technology, 2024,16(2):231-238

复制
分享
文章指标
  • 点击次数:73
  • 下载次数: 1033
  • HTML阅读次数: 271
  • 引用次数: 0
历史
  • 收稿日期:2023-06-14
  • 在线发布日期: 2024-04-03
  • 出版日期: 2024-03-28

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司