Hybrid prediction of photovoltaic power generation based on modal secondary decomposition and OOA-CNN-BiLSTM-Attention

doi:10.3969/j.issn.2097-0706.2025.09.004

Abstract

Abstract:

Due to the intermittency and instability of solar radiation， photovoltaic（PV） power generation shows high randomness and fluctuation， posing challenges to the stable operation of power grids. To improve prediction accuracy， the complete ensemble empirical mode decomposition with adaptive noise（CEEMDAN） was applied to decompose PV power data into intrinsic mode functions（IMFs） with different frequencies. These IMFs were clustered using K-means based on sample entropy， categorizing into high-， medium-， and low-frequency components. The high-frequency components were further decomposed using variational mode decomposition（VMD） for refined analysis. A hybrid deep learning prediction model was established by integrating convolutional neural network（CNN）， bidirectional long short-term memory （BiLSTM） network， and attention mechanism. The osprey optimization algorithm（OOA） was employed to optimize the model's hyperparameters. The experimental results showed that the proposed hybrid prediction model based on modal secondary decomposition and OOA-CNN-BiLSTM-Attention achieved a root mean square error of 4.11 kW， a mean absolute error of 2.88 kW， a mean absolute percentage error of 3.08%， and a coefficient of determination of 98.89%， outperforming other models. It is demonstrated that the proposed method effectively captures the multi-scale features of PV power generation with strong generalization ability and application potential.

Key words: photovoltaic power prediction, modal decomposition, convolutional neural network, BiLSTM neural network, attention mechanism

CLC Number:

TK519

LI Zhen, YANG Guohua, ZHANG Yuanxi, MA Xin, YANG Na, LIU Haorui, MA Longteng. Hybrid prediction of photovoltaic power generation based on modal secondary decomposition and OOA-CNN-BiLSTM-Attention[J]. Integrated Intelligent Energy, 2025, 47(9): 28-37.

Figures/Tables 14

Fig.1

Fig.2

Fig.3

Table 1

Fig.4

Fig.5

Fig.6

Fig.7

Table 2

Fig.8

Fig.9

Table 3

Fig.10

Table 4

References 29

[1]	周孝信, 陈树勇, 鲁宗相, 等. 能源转型中我国新一代电力系统的技术特征[J]. 中国电机工程学报, 2018, 38(7): 1893-1904, 2205.
	ZHOU Xiaoxin, CHEN Shuyong, LU Zongxiang, et al. Technology features of the new generation power system in China[J]. Proceedings of the CSEE, 2018, 38(7): 1893-1904, 2205.
[2]	王蓓蓓, 亢丽君, 苗曦云, 等. 考虑可信度的新能源及需求响应参与英美容量市场分析及思考[J]. 电网技术, 2022, 46(4): 1233-1247.
	WANG Beibei, KANG Lijun, MIAO Xiyun, et al. Analysis and enlightenment of renewable energy and demand response participating in UK and US capacity markets considering capacity credibility[J]. Power System Technology, 2022, 46(4): 1233-1247.
[3]	张赟宁, 魏广军. 考虑特征选择的短期光伏功率组合预测模型[J]. 电力系统及其自动化学报, 2024, 36(8): 122-132.
	ZHANG Yunning, WEI Guangjun. Combined prediction model for short-term photovoltaic power considering feature selection[J]. Proceedings of the CSU-EPSA, 2024, 36(8): 122-132.
[4]	SI Z Y, YANG M, YU Y X, et al. Photovoltaic power forecast based on satellite images considering effects of solar position[J]. Applied Energy, 2021, 302: 117514.
[5]	张永宁, 任晓颖, 张飞, 等. 基于深度学习的光伏功率预测技术[J/OL]. 综合智慧能源:1-8(2024-04-01)[2025-03-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240328.2244.002.html.
	ZHANG Yongning, REN Xiaoying, ZHANG Fei, et al. Photovoltaic power forecasting technology based on deep learning[J/OL]. Integrated Smart Energy:1-8(2024-04-01)[2025-03-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240328.2244.002.html.
[6]	朱琼锋, 李家腾, 乔骥, 等. 人工智能技术在新能源功率预测的应用及展望[J]. 中国电机工程学报, 2023, 43(8): 3027-3048.
	ZHU Qiongfeng, LI Jiateng, QIAO Ji, et al. Application and prospect of artificial intelligence technology in renewable energy forecasting[J]. Proceedings of the CSEE, 2023, 43(8): 3027-3048.
[7]	汪鸿, 朱正甲, 陈建华, 等. 基于人工智能技术与物理方法结合的新能源功率预测研究[J]. 高电压技术, 2023, 49(S1): 111-117.
	WANG Hong, ZHU Zhengjia, CHEN Jianhua, et al. Research on new energy power prediction based on artificial intelligence technology and physical method[J]. High Voltage Engineering, 2023, 49(S1): 111-117.
[8]	陈凡, 李智, 丁津津, 等. 考虑光伏机理与数据驱动结合的短期功率预测[J]. 科学技术与工程, 2023, 23(20): 8686-8692.
	CHEN Fan, LI Zhi, DING Jinjin, et al. Consider short-term power prediction combining photovoltaic mechanism and data-driven[J]. Science Technology and Engineering, 2023, 23(20): 8686-8692.
[9]	王东风, 刘婧, 黄宇, 等. 结合太阳辐射量计算与CNN-LSTM组合的光伏功率预测方法研究[J]. 太阳能学报, 2024, 45(2): 443-450. doi: 10.19912/j.0254-0096.tynxb.2022-1542
	WANG Dongfeng, LIU Jing, HUANG Yu, et al. Photovoltaic power prediction method combinating solar radiation calculation and CNN-LSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(2): 443-450. doi: 10.19912/j.0254-0096.tynxb.2022-1542
[10]	ALI A, AHMED A, MOUSSA L, et al. CNN-LSTM: An efficient hybrid deep learning architecture for predicting short-term photovoltaic power production[J]. Electric Power Systems Research, 2022, 208: 107908.
[11]	黄牧涛, 邢芳菲, 陈兴邦, 等. 基于K-means聚类和极限学习机组合算法的短期光伏功率预测[J]. 水电能源科学, 2024, 42(2): 217-220.
	HUANG Mutao, XING Fangfei, CHEN Xingbang, et al. Short-term PV power prediction based on K-means clustering and extreme learning machine combination algorithm[J]. Water Resources and Power, 2024, 42(2): 217-220.
[12]	马乐乐, 孔小兵, 郭磊, 等. 基于最大重叠离散小波变换和深度学习的光伏功率预测[J]. 太阳能学报, 2024, 45(5): 576-583.
	MA Lele, KONG Xiaobing, GUO Lei, et al. Photovoltaic power forecasting based on maximum overlap discrete wavelet transform and deep learning[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 576-583.
[13]	郭威, 孙胜博, 陶鹏, 等. 基于多元变分模态分解和混合深度神经网络的短期光伏功率预测[J]. 太阳能学报, 2024, 45(4): 489-499.
	GUO Wei, SUN Shengbo, TAO Peng, et al. Short-term photovoltaic power forecasting based on multivariate variational mode decomposition and hybrid deep neural network[J]. Acta Energiae Solaris Sinica, 2024, 45(4): 489-499.
[14]	程先龙, 张杰, 李思莹, 等. 基于VMD-BP-BiLSTM的短期风电功率预测[J/OL]. 综合智慧能源:1-10(2024-12-12)[2025-03-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20241211.1634.002.html.
	CHENG Xianlong, ZHANG Jie, LI Siying, et al. Short-term wind power prediction based on VMD-BP-BiLSTM[J/OL]. Integrated Intelligent Energy: 1-10(2024-12-12)[2025-03-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20241211.1634.002.html.
[15]	张海涛, 李文娟, 李雪峰, 等. 基于变分模态分解和时间注意力机制TCN网络的光伏发电功率预测[J]. 电测与仪表, 2024, 61(12): 156-163.
	ZHANG Haitao, LI Wenjuan, LI Xuefeng, et al. Photovoltaic power forecasting based on TPA-TCN model and variational modal decomposition[J]. Electrical Measurement Instrumentation, 2024, 61(12): 156-163.
[16]	梁亚峰, 马立红, 邱剑洪, 等. 基于CEEMD-LSTM光伏短期功率预测[J]. 科学技术与工程, 2024, 24(13): 5396-5405.
	LIANG Yafeng, MA Lihong, QIU Jianhong, et al. Short-term photovoltaic power forecasting based on CEEMD-LSTM[J]. Science Technology and Engineering, 2024, 24(13): 5396-5405.
[17]	王瑞, 闫豪, 逯静. 基于ICEEMDAN-MBWO-WKELM短期光伏功率预测[J]. 电力电子技术, 2024, 58(2): 59-63.
	WANG Rui, YAN Hao, LU Jing. Short-term photovoltaic power prediction based on ICEEMDAN-MBWO-WKELM[J]. Power Electronics, 2024, 58(2): 59-63.
[18]	袁俊球, 王迪, 谢小锋, 等. 基于广义天气分类的ICEEMDAN-LSTM网络光伏发电功率短期预测[J]. 综合智慧能源, 2024, 46(9): 53-60. doi: 10.3969/j.issn.2097-0706.2024.09.007
	YUAN Junqiu, WANG Di, XIE Xiaofeng, et al. Study of short-term PV power prediction based on ICEEMDAN-LSTM networks under generalized weather classifications[J]. Integrated Intelligent Energy, 2024, 46(9): 53-60. doi: 10.3969/j.issn.2097-0706.2024.09.007
[19]	夏晓荣, 胡鹏飞, 王飞, 等. 基于小波变换与优化BP神经网络的超短期光伏发电功率预测[J]. 电网与清洁能源, 2024, 40(10): 159-166.
	XIA Xiaorong, HU Pengfei, WANG Fei, et al. Ultra-short-term photovoltaic power prediction based on wavelet transform and optimal BP neural networks[J]. Power System and Clean Energy, 2024, 40(10): 159-166.
[20]	周鑫, 李燕, 曾永辉, 等. 基于SARIMAX-SVR的光伏发电功率预测[J]. 电力系统及其自动化学报, 2024, 36(5): 1-8.
	ZHOU Xin, LI Yan, ZENG Yonghui, et al. Forecasting of photovoltaic power generation based on SARIMAX-SVR[J]. Proceedings of the CSU-EPSA, 2024, 36(5): 1-8.
[21]	HUANG N, SHEN Z, LONG S, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings of the Royal Society A:Mathematical Physical and Engineering Sciences, 1998, 454(1971): 903-995.
[22]	WU Z H, HUANG N E. Ensemble empirical mode decomposition: A noise-assisted data analysis method[J]. Advances in Data Science and Adaptive Analysis, 2009, 1(1): 1-41.
[23]	TORRES M E, COLOMINAS M A, SCHLOTTHAUER G, et al. A complete ensemble empirical mode decomposition with adaptive noise[C]// 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague: IEEE, 2011: 22-27.
[24]	李芬, 孙凌, 王亚维, 等. 基于CEEMDAN-GSA-LSTM和SVR的光伏功率短期区间预测[J]. 上海交通大学学报, 2024, 58(6): 806-818. doi: 10.16183/j.cnki.jsjtu.2022.511
	LI Fen, SUN Ling, WANG Yawei, et al. Short-term interval forecasting of photovoltaic power based on CEEMDAN-GSA-LSTM and SVR[J]. Journal of Shanghai Jiao Tong University, 2024, 58(6): 806-818.
[25]	李争, 张杰, 徐若思, 等. 基于相似日聚类和PCC-VMD-SSA-KELM模型的短期光伏功率预测[J]. 太阳能学报, 2024, 45(2): 460-468. doi: 10.19912/j.0254-0096.tynxb.2022-1608
	LI Zheng, ZHANG Jie, XU Ruosi, et al. Short term photovoltaic power prediction based on similar day clustering and PCC-VMD-SSA-KELM model[J]. Acta Energiae Solaris Sinica, 2024, 45(2): 460-468. doi: 10.19912/j.0254-0096.tynxb.2022-1608
[26]	DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544.
[27]	王瑞, 张璐婷, 逯静. 基于新型相似日选取和VMD-NGO-BiGRU的短期光伏功率预测[J]. 湖南大学学报(自然科学版), 2024, 51(2): 68-80.
	WANG Rui, ZHANG Luting, LU Jing. Short term photovoltaic power prediction based on new similar day selection and VMD-NGO-BiGRU[J]. Journal of Hunan University (Natural Sciences), 2024, 51(2): 68-80.
[28]	殷林飞, 张依玲. 结合变分模态分解与三重卷积神经网络的光伏出力预测[J/OL]. 综合智慧能源:1-9(2024-09-11)[2025-03-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240910.1606.004.html.
	YIN Linfei, ZHANG Yiling. Photovoltaic power output prediction based on variational mode decomposition and triple convolutional neural networks[J/OL]. Integrated Intelligent Energy:1-9(2024-09-11)[2025-03-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240910.1606.004.html.
[29]	周育才, 肖添, 谢七月, 等. 基于聚类的HPO-BILSTM光伏功率短期预测[J]. 太阳能学报, 2024, 45(4): 512-518.
	ZHOU Yucai, XIAO Tian, XIE Qiyue, et al. Clustering-based HPO-BILSTM short-term prediction of PV power[J]. Acta Energiae Solaris Sinica, 2024, 45(4): 512-518.

特征	皮尔逊相关系数
温度	0.36
云层不透明度	0.62
露点温度	0.11
太阳散射辐射	0.44
太阳直接辐射	0.77
太阳总水平辐射	0.99
跟踪倾角辐射	0.91
大气可降水量	0.10
相对湿度	0.38
地面气压	0.02
风向	0.04
风速	0.04

参数	数值
学习率	0.004 138 4
LSTM层神经元数	39
L2正则化系数	0.000 401 5
最大训练轮数	10

模型	MAE/kW	MAPE/%	R²/%	RMSE/kW
1	5.21	15.74	96.33	6.45
2	3.21	12.07	98.40	4.66
3	3.12	10.59	98.50	4.43
4	3.49	11.92	98.32	4.43
5	3.22	11.74	98.46	4.45
6	2.88	3.08	98.89	4.11

模型	MAE/kW	MAPE/%	R²/%	RMSE/kW
7	3.00	11.19	98.58	4.32
8	3.15	3.28	98.45	4.53
9	2.81	10.95	98.71	4.19
10	3.03	11.28	98.57	4.32
11	3.01	12.67	98.56	4.33
12	2.97	5.96	98.77	4.28