Power forecast of photovoltaic generation based on XGBoost combined model

被引：0
|
作者：
Wang X. [1 ]
Zeng S. [1 ]
Zhou X. [1 ]
Chen T. [1 ]
Guo S. [1 ]
Zhang W. [1 ]
机构：
[1] State Grid Hebei Electric Power Research Institute, Shijiazhuang
来源：
Taiyangneng Xuebao/Acta Energiae Solaris Sinica | 2022年 / 43卷 / 04期
关键词：
Combined model; Partial least squares; Photovoltaic power generation forecast; XGBoost;
D O I：
10.19912/j.0254-0096.tynxb.2020-0890
中图分类号：
学科分类号：
摘要：
This paper proposes a XGBoost combined model considering time series and multi-features for forecasting photovoltaic power. First, the multiple features is extracted that affect photovoltaic power based on partial least squares (PLS), then, the single PV power prediction models is established considering time series and multi-feature, respectively, based on XGBoost algorithm. Finally, the combined forecast model based on XGBoost is established through the training linear model parameters. The proposed XGBoost combined model is verified by the operation data of photovoltaic power plants in a certain area. As the results, the model has higher prediction accuracy, stronger generalization ability and stronger resistance to noise data. © 2022, Solar Energy Periodical Office Co., Ltd. All right reserved.
引用
收藏
页码：236 / 242
页数：6
相关论文
共 18 条
  • [1] LYU X, LIU T Y, DONG X Y, Et al., Outlook and prospect of the photovoltaic and wind power industry in 2019, Journal of Beijing Institute of Technology (social science edition), 21, 2, pp. 25-29, (2019)
  • [2] HICHEM H, CHIHEB B R, ABDERRAHMEN Z., A sliding-neural network control of induction-motor-pump supplied by photovoltaic generator, Protection and control of modern power systems, 5, 1, pp. 1-17, (2020)
  • [3] ZHAO L, LIU Y B, YU L N, Et al., Short-term power generation forecast of PV power station based on deep belief network, Power system protection and control, 47, 18, pp. 11-19, (2019)
  • [4] ALMONACID, PEREZ P J, FERNANDEZ E F, Et al., A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator, Energy conversion and management, 85, pp. 389-398, (2014)
  • [5] WANG J T, WANG W C, CHEN H W., Photovoltaic power generation forecasting based on regression-Markov chain, Electrical measurement & instrumentation, 56, 1, pp. 76-81, (2019)
  • [6] ZHANG Q, MA Y, LI G L, Et al., Applications of frequency domain decomposition and deep learning algorithms in short-term load and photovoltaic power forecasting, Proceedings of the CSEE, 39, 8, pp. 2221-2230, (2019)
  • [7] PENG S R, ZHENG G D, HUANG S J, Et al., Multiple-feature short-term photovoltaic generation forecasting based on XGBoost algorithm, Electrical measurement & instrumentation, 57, 24, pp. 76-83, (2020)
  • [8] LI Z M, LIANG C X, WANG M S., Short-term power generation output prediction based on a PSO-DBN neural network, Power system protection and control, 48, 8, pp. 149-154, (2020)
  • [9] DING K, DING H X, WANG Y, Et al., Short-term power prediction of photovoltaic array based on lifting wavelet transform-BP neural network, Renewable energy resources, 35, 4, pp. 566-571, (2017)
  • [10] YU Q L, XU C Q, LI S, Et al., Application of fuzzy clustering algorithm and support vector machine to short-term forecasting of PV power, Proceedings of the CSU-EPSA, 28, 12, pp. 115-118, (2016)
12