基于XGBoost-LSTM组合模型的光伏发电功率预测

谭海旺; 杨启亮; 邢建春; 黄克峰; 赵硕; 胡浩宇

doi:10.19912/j.0254-0096.tynxb.2021-0005

PDF(1694 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (8) : 75-81. DOI: 10.19912/j.0254-0096.tynxb.2021-0005

基于XGBoost-LSTM组合模型的光伏发电功率预测

谭海旺¹, 杨启亮¹, 邢建春¹, 黄克峰¹, 赵硕², 胡浩宇¹

作者信息 +

PHOTOVOLTAIC POWER PREDICTION BASED ON COMBINED XGBOOST-LSTM MODEL

Tan Haiwang¹, Yang Qiliang¹, Xing Jiangchun¹, Huang Kefeng¹, Zhao Shuo², Hu Haoyu¹

Author information +

文章历史 +

摘要

该文提出一种基于极端梯度提升（XGBoost）模型和长短期记忆网络（LSTM）模型的短期光伏发电功率预测组合模型。根据短期光伏发电特性,首先分别建立XGBoost模型和LSTM模型,然后利用XGBoost模型进行初步预测增加特征,并利用误差倒数法将两模型组合起来进行预测。选取2018年光伏电站人工智能运维大数据处理分析大赛的数据集进行实验评估,最终结果表明,该文所构建的XGBoost-LSTM组合模型的均方根误差（RMSE）为0.214,将上述方法与随机森林、GBDT模型和单一的XGBoost模型和LSTM模型相比较,该文提出的方法具有更高的预测精度。

Abstract

A combination model based on XGBoost（eXtreme Gradient Boosting） model and LSTM（Long Short Term Memory） model is proposed in this paper. According to the characteristics of short-term photovoltaic power generation, the XGBoost model and the LSTM model are established respectively in the first place. Then, the XGBoost model is used for preliminary prediction to add features, and the error reciprocal method is used to combine the two models for prediction. Data sets from 2018 big data processing and analysis contest of photovoltaic power station artificial intelligence operation and maintenance are selected for experimental evaluation. The final result shows that the root-mean-square error (RMSE) of the constructed XGBoost-LSTM combination model is 0.214. Compared with the Random Forest, GBDT model, XGBoost model, LSTM model, the proposed method has higher prediction accuracy.

导出引用

谭海旺, 杨启亮, 邢建春, 黄克峰, 赵硕, 胡浩宇. 基于XGBoost-LSTM组合模型的光伏发电功率预测[J]. 太阳能学报. 2022, 43(8): 75-81 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0005

Tan Haiwang, Yang Qiliang, Xing Jiangchun, Huang Kefeng, Zhao Shuo, Hu Haoyu. PHOTOVOLTAIC POWER PREDICTION BASED ON COMBINED XGBOOST-LSTM MODEL[J]. Acta Energiae Solaris Sinica. 2022, 43(8): 75-81 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0005

中图分类号： TM615

参考文献

[1] 江华, 金艳梅, 叶幸, 等. 中国光伏产业2019年回顾与2020年展望[J]. 太阳能, 2020(3): 14-23.
JIANG H, JIN Y M, YE X, et al. Review of China's PV industry in2019 and prospect in 2020[J]. Solar energy, 2020(3): 14-23.
[2] International Energy Agency.Technology roadmap solar photovoltaic energy[R]. Paris, 2010.
[3] 崔洋, 孙银川, 常倬林. 短期太阳能光伏发电预测方法研究进展[J]. 资源科学, 2013, 35(7): 1474-1481.
CUI Y, SUN Y C, CHANG Z L.A review of short-term solar photovoltaic power generation prediction methods[J]. Resources science, 2013, 35(7): 1474-1481.
[4] 赵滨滨, 王莹, 王彬, 等. 基于ARIMA时间序列的分布式光伏系统输出功率预测方法研究[J]. 可再生能源, 2019, 37(6): 820-823.
ZHAO B B, WANG Y, WANG B, et al.Photovoltaic power prediction in distribution network based on ARIMA model time series[J]. Renewable energy resources, 2019, 37(6): 820-823.
[5] 栗然, 李广敏. 基于支持向量机回归的光伏发电出力预测[J]. 中国电力, 2008(2): 74-78.
LI R, LI G M.Photovoltaic power generation output forecasting based on support vector machine regression technique[J]. Electric power, 2008(2): 74-78.
[6] AHMAD A, JIN Y, ZHU C A, et al.Support vector machine based prediction of photovoltaic module and power station parameters[J]. International journal of green energy, 2020, 17(3): 219-232.
[7] 王继拓, 王万成, 陈宏伟. 基于回归——马尔科夫链的光伏发电功率预测[J]. 电测与仪表, 2019, 56(1): 76-81.
WANG J T, WANG W C, CHEN H W.Photovoltaic power generation forecasting based on regression-Markov chain[J]. Electrical measurement & instrumentation, 2019, 56(1): 76-81.
[8] 吴长林, 陈玉, 高文根. 基于VMD-IPSO-RFR模型的光伏发电功率预测[J]. 四川轻化工大学学报(自然科学版), 2020, 33(2): 73-79.
WU C L, CHEN Y, GAO W G.Photovoltaic power prediction based on VMD-IPSO-RFR Model[J]. Journal of Sichuan University of Science & Engineering(natural science edition), 2020, 33(2): 73-79.
[9] 王晨阳, 段倩倩, 周凯, 等. 基于遗传算法优化卷积长短记忆混合神经网络模型的光伏发电功率预测[J]. 物理学报, 2020, 69(10): 149-155.
WANG C Y, DUAN Q Q, ZHOU Kai, et al.A hybrid model for photovoltaic power prediction of both convolutional and long short-term memory neural networks optimized by genetic algorithm[J]. Acta physica sinica, 2020, 69(10): 149-155.
[10] 王超洋, 张蓝宇, 刘铮, 等. 基于特征挖掘的indRNN光伏发电功率预测[J]. 电力系统及其自动化学报, 2021, 33(4): 17-22.
WANG C Y, ZHANG L Y, LIU Z, et al.Photovoltaic power prediction based on feature mining and indRNN[J] Proceedings of the CSU-EPSA, 2021, 33(4): 17-22.
[11] 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 D L, WANG Y, YU Y X, 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.
[12] 胡克用, 李云龙, 江霞, 等. 改进神经网络模型在光伏发电预测中的应用[J]. 计算机系统应用, 2019, 28(12): 37-46.
HU K Y, LI Y L, JIANG X, et al.Application of improved neural network model in photovoltaic power generation prediction[J]. Computer systems & applications, 2019, 28(12): 37-46.
[13] 彭曙蓉, 郑国栋, 黄士峻, 等. 基于XGBoost算法融合多特征短期光伏发电量预测[J]. 电测与仪表, 2020, 57(24): 76-83.
PENG S R, ZHENG G D, HUANG S J, et al.Multiple-feature short-term photovoltaic generation forecasting based on XGBoost algorithm[J]. Electrical measurement & instrumentation, 2020, 57(24): 76-83.
[14] 唐雅洁, 林达, 倪筹帷, 等. 基于XGBoost的双层协同实时校正超短期光伏预测[J]. 电力系统自动化, 2021, 45(7): 18-27.
TANG Y J, LIN D, NI C W, et al.XGBoost based bi-layer collaborative real-time calibration for ultra-short-term photovoltaic prediction[J]. Automation of electric power systems, 2021, 45(7): 18-27.
[15] 陈瑶, 陈晓宁. 基于自适应Kmeans和LSTM的短期光伏发电预测[J/OL]. 电测与仪表: 1-5. https://kns-cnki-net-s.nudtproxy.yitlink.com:443/kcms/detail/23.1202.TH.20200521.1438.014.html.
CHEN Y, CHEN X N. Prediction of short-term photovoltaic power generation based on adaptive Kmeans and LSTM[J]. Electrical measurement & instrumentation: 1-5.https://kns-cnki-net-s.nudtproxy.yitlink.com:443/kcms/detail/23.1202.TH.20200521.1438.014.html.
[16] 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.
MA L, HUANG W, LI K C, et al.Photovoltaic ultra short-term power forecasting model based on Attention-LSTM[J]. Electrical measurement & instrumentation, 2021, 58(2): 146-152.
[17] 陈振宇, 刘金波, 李晨, 等. 基于LSTM与XGBoost组合模型的超短期电力负荷预测[J]. 电网技术, 2020, 44(2): 614-620.
CHEN Z Y, LIU J B, LI C, et al.Ultra short-term power load forecasting based on combined LSTM-XGBoost model[J]. Power system technology, 2020, 44(2): 614-620.
[18] 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.
[19] 史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法[J]. 中国电机工程学报, 2019, 39(14): 4032-4042.
SHI J Q, ZHANG J H.Load forecasting based on multi-model by stacking ensemble learning[J]. Proceedings of the CSEE, 2019, 39(14): 4032-4042.
[20] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802.
ZHU Q M, LI H Y, WANG Z Q, et al.Short-term wind power forecasting based on LSTM[J]. Power system technology, 2017, 41(12): 3797-3802.
[21] HUANG C, WANG L, YEUNG R S, et al.A prediction model-guided Jaya algorithm for the PV system maximum power point tracking[J]. IEEE transactions on sustainable energy, 2017, 9(1): 45-55.
[22] 光伏电站人工智能运维大数据处理分析[DB/OL]. [2018-07-13].https://www.datafountain.cn/competitions/303/datasets.html.
Big data processing and analysis of artificial intelligence operation and maintenance of power station[DB/OL]. [2018-07-13].https://www.datafountain.cn/competitions/303/datasets.html.
[23] TRABEA A A, SHALTOUT M A M. Correlation of global solar radiation with meteorological parameters over Egypt[J]. Renewable energy, 2000, 21(2): 297-308.
[24] 吴思博, 陈志刚, 黄瑞. 基于相关系数的ID3优化算法[J]. 计算机工程与科学, 2016, 38(11): 2342-2347.
WU S B, CHEN Z G, HUANG R.An improved ID3 algorithm based on correlation coefficients[J]. Computer engineering & science, 2016, 38(11): 2342-2347.
[25] 范高锋, 王伟胜, 刘纯. 基于人工神经网络的风电功率短期预测系统[J]. 电网技术, 2008, 32(22): 72-76.
FAN G F, WANG W S, LIU Chun.Artificial neural network based wind power short term prediction system[J]. Power system technology, 2008, 32(22): 72-76.