融合PCC-LSTM-XGBoost的中长期光伏功率预测模型

密伟; 蒋旭; 晁梓博; 潘风文; 雷宇

doi:10.19912/j.0254-0096.tynxb.2024-1883

PDF(3608 KB)

太阳能学报 ›› 2026, Vol. 47 ›› Issue (2) : 155-164. DOI: 10.19912/j.0254-0096.tynxb.2024-1883

融合PCC-LSTM-XGBoost的中长期光伏功率预测模型

密伟, 蒋旭, 晁梓博, 潘风文, 雷宇

作者信息 +

PREDICTION MODEL FOR MID- AND LONG-TERM PHOTOVOLTAIC POWER BASED ON INTEGRATION OF PCC-LSTM-XGBoost

Mi Wei, Jiang Xu, Chao Zibo, Pan Fengwen, Lei Yu

Author information +

文章历史 +

摘要

针对传统光伏发电功率预测模型在预测精度和泛化能力上的不足,该文设计并实现一种耦合PCC、LSTM与XGBoost算法的预测模型。首先,利用皮尔逊相关系数（PCC）对影响太阳电池发电功率的多维度特征进行筛选,构建优化的输入特征集;其次,通过长短期记忆网络（LSTM）建模时间序列数据中的长期依赖关系,获得初步的功率预测;同时,引入极端梯度提升树（XGBoost）算法对光伏发电功率的特征进行非线性建模和预测。最后,通过LSTM和XGBoost的预测结果进行策略融合得到预测结果,以提高预测精度和泛化能力。实验结果表明,该文提出的融合模型在中长期光伏功率预测中具有更高的精度和稳定性,模型的预测效果显著优于传统方法。由此可见,该文提出的PCC-LSTM-XGBoost模型为光伏发电功率的精确预测提供了新的技术途径,特别适用于不同的气候条件场景下的光伏电站功率预测。

Abstract

To address the limitations of traditional photovoltaic （PV） power prediction models in terms of forecasting accuracy and generalization capability, this paper designs and implements a prediction model that couples PCC, LSTM and XGBoost algorithms. Firstly, PCC is utilized to filter multi-dimensional features that influence PV power generation, thus constructing an optimized input feature set. Secondly, LSTM network is employed to model the long-term dependencies within the time series data, providing an initial power prediction. Concurrently, the XGBoost algorithm is introduced to model and predict the non-linear features of PV power generation. Finally, this paper lies in enhancing prediction accuracy and generalization capabilities by integrating the prediction results from LSTM and XGBoost models. Experimental results demonstrate that the proposed fusion model exhibits higher accuracy and stability in mid-and long-term PV power rolling forecasts, significantly outperforming traditional methods. Therefore, the proposed PCC-LSTM-XGBoost model offers a novel technical approach for accurate PV power prediction, making it particularly suitable for forecasting PV station power under various climatic conditions.

导出引用

密伟, 蒋旭, 晁梓博, 潘风文, 雷宇. 融合PCC-LSTM-XGBoost的中长期光伏功率预测模型[J]. 太阳能学报. 2026, 47(2): 155-164 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1883

Mi Wei, Jiang Xu, Chao Zibo, Pan Fengwen, Lei Yu. PREDICTION MODEL FOR MID- AND LONG-TERM PHOTOVOLTAIC POWER BASED ON INTEGRATION OF PCC-LSTM-XGBoost[J]. Acta Energiae Solaris Sinica. 2026, 47(2): 155-164 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1883

中图分类号： TM615

参考文献

[1] DHAKED D K, DADHICH S, BIRLA D.Power output forecasting of solar photovoltaic plant using LSTM[J]. Green energy and intelligent transportation, 2023, 2(5): 100113.
[2] NI Q, ZHUANG S X, SHENG H M, et al.An optimized prediction intervals approach for short term PV power forecasting[J]. Energies, 2017, 10(10): 1669.
[3] 陈庆明, 廖鸿飞, 孙颖楷, 等. 基于GWO-GRU的光伏发电功率预测[J]. 太阳能学报, 2024, 45(7): 438-444.
CHEN Q M, LIAO H F, SUN Y K, et al.Power prediction of photovoltaic generation based on GWO-GRU[J]. Acta energiae solaris sinica, 2024, 45(7): 438-444.
[4] ALARAJ M, ALSAIDAN I, KUMAR A, et al.Advanced intelligent approach for solar PV power forecasting using meteorological parameters for Qassim region, Saudi Arabia[J]. Sustainability, 2023, 15(12): 1-16.
[5] TAVARES I, MANFREDINI R, ALMEIDA J, et al.Comparison of PV power generation forecasting in a residential building using ANN and DNN[J]. IFAC-PapersOnLine, 2022, 55(9): 291-296.
[6] 张成, 白建波, 兰康, 等. 基于数据挖掘和遗传小波神经网络的光伏电站发电量预测[J]. 太阳能学报, 2021, 42(3): 375-382.
ZHANG C, BAI J B, LAN K, et al.Photovoltaic power generation prediction based on data mining and genetic wavelet neural network[J]. Acta energiae solaris sinica, 2021, 42(3): 375-382.
[7] 王俊杰, 毕利, 张凯, 等. 基于多特征融合和XGBoost-LightGBM-ConvLSTM的短期光伏发电量预测[J]. 太阳能学报, 2023, 44(7): 168-174.
WANG J J, BI L, ZHANG K, et al.Short-term photovoltaic power generation prediction based on multi-feature fusion and XGBoost-LightGBM-ConvLSTM[J]. Acta energiae solaris sinica, 2023, 44(7): 168-174.
[8] 刘国海, 孙文卿, 吴振飞, 等. 基于Attention-GRU的短期光伏发电功率预测[J]. 太阳能学报, 2022, 43(2): 226-232.
LIU G H, SUN W Q, WU Z F, et al.Short-term photovoltaic power forecasting based on Attention-GRU[J]. Acta energiae solaris sinica, 2022, 43(2): 226-232.
[9] 姚宏民, 杜欣慧, 秦文萍. 基于密度峰值聚类及GRNN神经网络的光伏发电功率预测方法[J]. 太阳能学报, 2020, 41(9): 184-190.
YAO H M, DU X H, QIN W P.PV power forecasting approach based on density peaks clustering and general regression neural network[J]. Acta energiae solaris sinica, 2020, 41(9): 184-190.
[10] 吴珺玥, 赵二刚, 郭增良, 等. 基于Spearman系数和TCN的光伏出力超短期多步预测[J]. 太阳能学报, 2023, 44(9): 180-186.
WU J Y, ZHAO E G, GUO Z L, et al.Ultra-short-term photovoltaic power multi-step prediction based on Spearman coefficient and TCN[J]. Acta energiae solaris sinica, 2023, 44(9): 180-186.
[11] 刘刚, 闵金, 宋伟, 等. 基于K-Means和GBRT的分布式光伏中短期发电量预测[J]. 能源与环保, 2023, 45(3): 210-215, 221.
LIU G, MIN J, SONG W, et al.Medium-short term power generation prediction of distributed photovoltaic based on K-Means and GBRT[J]. China energy and environmental protection, 2023, 45(3): 210-215, 221.
[12] 李超, 涂腾, 彭勋辉. 融合DT-BO-GRU 的中长期光伏功率滚动预测模型[J]. 太阳能学报, 2025, 46(5): 275-284.
LI C, TU T, PENG X H.Medium and long-term photovoltaic power rolling prediction model based on fusion DT-BO-GRU[J]. Acta energiae solaris sinica, 2025, 46(5): 275-284.
[13] 陈元峰, 马溪原, 程凯, 等. 基于气象特征量选取与SVM模型参数优化的新能源超短期功率预测[J]. 太阳能学报, 2023, 44(12): 568-576.
CHEN Y F, MA X Y, CHENG K, et al.Ultra-short-term power forecast of new energy based on meteorological feature selection and SVM model parameter optimization[J]. Acta energiae solaris sinica, 2023, 44(12): 568-576.
[14] 高寒旭, 袁祖晴, 张淑婷, 等. 基于LSTM模型的短期光伏功率预测[J]. 太阳能学报, 2024, 45(6): 376-381.
GAO H X, YUAN Z Q, ZHANG S T, et al.Short-term photovoltaic power prediction based on LSTM model[J]. Acta energiae solaris sinica, 2024, 45(6): 376-381.
[15] 王永生, 李海龙, 关世杰, 等. 基于变换域分析和XGBoost算法的超短期风电功率预测模型[J]. 高电压技术, 2024, 50(9): 3860-3870.
WANG Y S, LI H L, GUAN S J, et al.Ultra-short-term wind power prediction model based on transform domain analysis and XGBoost algorithm[J]. High voltage engineering, 2024, 50(9): 3860-3870.
[16] 高驰涵, 张梅, 陈哲, 等. 基于随机森林与长短期记忆网络结合的蓝莓黑腹果蝇发生预测[J]. 山东农业科学, 2024, 56(8): 158-164.
GAO C H, ZHANG M, CHEN Z, et al.Prediction of blueberry drosophila melanogaster occurrence based on random forest combined with long short-term memory network[J]. Shandong agricultural sciences, 2024, 56(8): 158-164.
[17] 孟亦康, 许野, 王鑫鹏, 等. 基于相似日选取和PCA-LSTM的光伏出力组合预测模型研究[J]. 太阳能学报, 2024, 45(7): 453-461.
MENG Y K, XU Y, WANG X P, et al.Research on photovoltaic output combination prediction model based on similar day selection and PCA-LSTM[J]. Acta energiae solaris sinica, 2024, 45(7): 453-461.
[18] 王瑶, 吴云来, 俞铁铭, 等. 基于特征选择和XGBoost算法考虑极端天文、气象事件影响的光伏性能预测方法[J]. 太阳能学报, 2024, 45(5): 547-555.
WANG Y, WU Y L, YU T M, et al.Forecasting method of photovoltaic power generation based on feature selection and XGBoost algorithm considering influence of extreme astronomical and meteorological events[J]. Acta energiae solaris sinica, 2024, 45(5): 547-555.
[19] 李特, 王尧, 武文起, 等. 机器学习在光伏发电功率预测中的应用分析[J]. 河北电力技术, 2024, 43(3): 55-61.
LI T, WANG Y, WU W Q, et al.Application of machine learning in photovoltaic power generation prediction[J]. Hebei electric power, 2024, 43(3): 55-61.