针对现有深度学习预测模型在训练过程中存在的时间较长、易陷入局部最优解等问题,提出一种基于开普勒优化算法（KOA）驱动的VMD-CNN-BiGRU-Attention短期光伏出力预测方法。该方法首先利用皮尔逊相关系数法对关键气象因素进行筛选;随后采用灰色关联度（GRA）法确定待预测日的历史相似日,并通过KOA对变分模态分解（VMD）的参数进行优化,进而对历史相似日的出力序列进行分解,从而生成高质量的模型训练样本集;最后,基于KOA-CNN-BiGRU-Attention算法构建光伏出力组合预测模型,以实现光伏出力的精准预测。在云南和甘肃两地光伏电站的实际应用表明,该模型的均方根误差（RMSE）分别为0.2540、2.7981 MW,平均绝对百分比误差（MAPE）分别为0.0234、1.1699。与其他组合预测模型相比,所提基于KOA驱动的VMD-CNN-BiGRU-Attention模型在时空特征捕捉能力方面具有显著优势,并在预测精度和稳定性上表现出优越性,展现了其在光伏发电预测领域的广阔应用潜力。
Abstract
To address the challenges of existing deep learning prediction models, such as long training times and a tendency to fall into local optimum, this paper proposes an innovative KOA-driven VMD-CNN-BiGRU-Attention method for short-term photovoltaic （PV） output power prediction. Firstly, the Pearson correlation coefficient is employed to identify key meteorological factors. Then, the grey relational analysis （GRA） method is used to determine the historical similarity days for the predicted days. The Keplerian Optimization Algorithm （KOA） is then used to optimize the parameters of variational mode decomposition （VMD）, which decomposes the output sequences of historical similarity days to generate a high-quality training sample set. Finally, the VMD-CNN-BiGRU-Attention model, driven by KOA, is constructed to achieve accurate PV output power prediction. Practical applications at PV power stations in Yunnan and Gansu show that the model achieves RMSE values of 0.2540 MW and 2.7981 MW, and MAPE values of 0.0234 and 1.1699, respectively. Compared with other combined prediction models, the proposed KOA-driven VMD-CNN-BiGRU-Attention model demonstrates superior ability to capture spatiotemporal features, offering significant improvements in prediction accuracy and stability. These results highlight the broad application potential of the model in PV power generation prediction.
关键词
光伏出力预测 /
开普勒优化算法 /
变分模态分解 /
注意力机制 /
CNN-BiGRU-Attention组合模型
Key words
PV output prediction /
Keplerian optimization algorithm （KOA） /
variational mode decomposition （VMD） /
Attention mechanism /
CNN-BiGRU-Attention combined model
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 贾凌云, 云斯宁, 赵泽妮, 等. 神经网络短期光伏发电预测的应用研究进展[J]. 太阳能学报, 2022, 43(12): 88-97.
JIA L Y, YUN S N, ZHAO Z N, et al.Recent progress of short-term forecasting of photovoltaic generation based on artificia neural networks[J]. Acta energiae solaris sinica1, 2022, 43(12): 88-97.
[2] 刘甚臻, 马超. 基于小波变换和混合深度学习的短期光伏功率预测[J]. 可再生能源, 2023, 41(6): 744-749.
LIU S Z,MA C.Short-term photovoltaic power prediction based on wavelet transform and hybrid deep learning[J]. Renewable energy resources, 2023, 41(6): 744-749.
[3] LI Q, ZHANG X, MA T, et al.A multi-step ahead photovoltaic power prediction model based on similar day, enhanced colliding bodies optimization, variational mode decomposition, and deep extreme learning machine[J]. Energy, 2021, 224(2): 120094-120094.
[4] 张大海, 孙锴, 和敬涵. 基于相似日与多模型融合的短期负荷预测[J]. 电网技术, 2023, 47(5): 1961-1970.
ZHANG D H, SUN K, HE J H.Short-term load forecasting based on similar day and multi-model fusion[J]. Power system technology, 2023, 47(05): 1961-1970.
[5] 阎洁, 许成志, 刘永前, 等. 基于风速云模型相似日的短期风电功率预测方法[J]. 电力系统自动化, 2018, 42(6): 53-59.
YAN J, XU C Z, LIU Y Q, et al.Short-term wind power prediction method based on wind speed cloud model in similar day[J]. Automation of electric power systems, 2018, 42(6): 53-59.
[6] 薛阳, 李金星, 杨江天, 等. 基于相似日分析和改进鲸鱼算法优化LSTM网络模型的光伏功率短期预测[J]. 南方电网技术, 2024, 18(11): 97-105.
XUE Y, LI J X, YANG J T, et al.Short-term prediction of photovoltaic power based on similar day analysis and improved whale algorithm to optimize LSTM network model[J]. Southern power system technology, 2024, 18(11): 97-105.
[7] 李练兵, 高国强, 陶鹏, 等. 基于SFLA和MSISSA-ANFIS的超短期光伏功率动态预测方法[J]. 太阳能学报, 2024, 45(10): 326-335.
LI L B,GAO G Q,T P, et al. Ultra-short-term PV power dynamic prediction method based on SFLA and MSISSA-ANFIS[J]. Acta energiae solaris sinica, 2024, 45(10): 326-335.
[8] 张程, 林谷青, 黄靖, 等. 基于AMBOA-DBN结合相似日的短期光伏功率预测[J]. 太阳能学报, 2023, 44(6): 290-299.
ZHANG C,LIN G Q,HUANG J, et al.Short-term PV power prediction based on AMBOA-DBN combined with similar days[J]. Acta energiae solaris sinica, 2023, 44(6): 290-299.
[9] 孟安波, 陈嘉铭, 黎湛联, 等. 基于相似日理论和CSO-WGPR的短期光伏发电功率预测[J]. 高电压技术, 2021, 47(4): 1176-1184.
MENG A B, CHEN J M, LI Z L,et al.Short-term photovoltaic power generation prediction based on similar day theory and CSO-WGPR[J]. High voltage engineering, 2021, 47(4): 1176-1184.
[10] 张雲钦, 程起泽, 蒋文杰, 等. 基于EMD-PCA-LSTM的光伏功率预测模型[J]. 太阳能学报, 2021, 42(9): 62-69.
ZHANG YQ,CHEN QZ,JIANG WJ, et al.Photovoltaic power prediction model based on EMD-PCA-LSTM[J]. Acta energiae solaris sinica, 2021, 42(9): 62-69.
[11] 张飞, 张志伟, 万乐斐, 等. 基于EEMD-GRNN方法的光伏电站短期出力预测[J]. 太阳能学报, 2020, 41(12): 103-109.
ZHANG F, ZHANG Z W, WAN L F, et al.Short-term output prediction of photovoltaic power station based on EEMD-GRNN method[J]. Acta energiae solaris sinica,2020, 41(12): 103-109.
[12] 茆美琴, 龚文剑, 张榴晨, 等. 基于EEMD-SVM方法的光伏电站短期出力预测[J]. 中国电机工程学报, 2013, 33(34): 17-29.
MAO M Q, GONG W J, ZHANG L C, et al.Short-term photovoltaic generation forecasting based on EEMD-SVM combined method[J]. Proceedings of the CSEE, 2013, 33(34): 17-29.
[13] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
WANG X X,YU M,JI M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta energiae solaris sinica, 2023, 44(6): 275-283.
[14] 林文婷, 李培强, 荆志宇, 等. 基于多级特征提取的BiLSTM短期光伏出力预测[J]. 太阳能学报, 2024, 45(10): 284-297.
LIN W T, LI P Q, JING Z Y, et al.Short-term photovoltaic output prediction based on multi-level feature extraction using BiLSTM[J]. Acta energiae solaris sinica, 2024, 45(10): 284-297.
[15] WANG S J, LIU S, GUAN X.Ultra-short-term power prediction of a photovoltaic power station based on the VMD-CEEMDAN-LSTM model[J]. Frontiers in energy research, 2022, 10:945327.
[16] 李超然, 潘鹏程, 杨伟荣, 等. 基于改进相似日优化HBA-BiLSTM-KELM的光伏发电功率预测[J]. 太阳能学报, 2024, 45(5): 508-516.
LI C R,PAN P C,YANG W R, et al.Research on PV system power prediction based on improved similar day and HBA-BiLSTM-KELM neural network[J]. Acta energiae solaris sinica,2024, 45(5): 508-516.
[17] 李云松, 张智晟. 基于GRU-TGTransformer的综合能源系统多元负荷短期预测[J]. 电力系统保护与控制, 2023, 51(15): 33-41.
LI Y S, ZHANG Z S.Multi load short-term forecasting of an integrated energy system based on a GRU-TGTransformer[J]. Power system protection and control, 2023, 51(15): 33-41.
[18] 彭曙蓉, 陈慧霞, 孙万通, 等. 基于改进LSTM的光伏发电功率预测方法研究[J]. 太阳能学报, 2024, 45(11): 296-302.
CAI S R, CHEN H X, SUN W T, et al.Research on photovoitaic power prediction method based on improved LSTM[J]. Acta energiae solaris sinica, 2024, 45(11): 296-302.
基金
中央高校基本科研业务费专项资金（2025MS050）
PDF(1371 KB)
