SHORT-TERM PHOTOVOLTAIC POWER PREDICTION BASED ON VMD AND DUAL ATTENTION MECHANISM

He Hucheng; Cao Haoyu; Sun Kai; Luo Yu

doi:10.19912/j.0254-0096.tynxb.2025-1110

PDF(1301 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (12) : 163-172. DOI: 10.19912/j.0254-0096.tynxb.2025-1110

SHORT-TERM PHOTOVOLTAIC POWER PREDICTION BASED ON VMD AND DUAL ATTENTION MECHANISM

He Hucheng, Cao Haoyu, Sun Kai, Luo Yu

Author information +

History +

Abstract

To address the challenges of strong non-stationarity in PV power sequences and low accuracy of single-model prediction, this paper proposes a short-term PV power prediction method optimized by variational mode decomposition （VMD） and a dual attention mechanism. Firstly, VMD is employed to decompose the original power signal into multiple frequency mode sub-sequences, and the separate prediction models are constructed for each sub-sequence to effectively capture spatial features and temporal dependencies. Then, a convolutional neural network enhanced with a channel attention mechanism （CNN-SE） is designed to improve the recognition of key features. Meanwhile, a self-attention mechanism is integrated to further exploit long-term temporal dependencies within the long short-term memory （LSTM） network. The final output is obtained by weighted fusion of all sub-sequence predictions. Case studies based on real-world data from a PV power station in Australia, along with comparative analysis against other mainstream methods, demonstrate the effectiveness of the proposed approach in handling non-stationary data and improving prediction accuracy.

Key words

photovoltaic power prediction / variational mode decomposition / convolutional neural network / long short-term memory network / self-attention / channel attention

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

He Hucheng, Cao Haoyu, Sun Kai, Luo Yu. SHORT-TERM PHOTOVOLTAIC POWER PREDICTION BASED ON VMD AND DUAL ATTENTION MECHANISM[J]. Acta Energiae Solaris Sinica. 2026, 47(12): 163-172 https://doi.org/10.19912/j.0254-0096.tynxb.2025-1110

References

[1] 吴梦丹, 张俊礼, 吴嘉峰, 等. 基于经济模型预测控制的光伏光热一体化热泵系统动态能效优化[J]. 中国电机工程学报, 2023, 43(6): 2119-2129.
Wu M D, Zhang J L, Wu J F, et al.Dynamic energy efficiency optimization of photovoltaic/thermal integrated heat pump system based on economic model predictive control[J]. Proceedings of the CSEE, 2023, 43(6): 2119-2129.
[2] 董存, 王铮, 白捷予, 等. 光伏发电功率超短期预测方法综述[J]. 高电压技术, 2023, 49(7): 2938-2951.
Dong C, Wang Z, Bai J Y, et al.Review of ultra-short-term forecasting methods for photovoltaic power generation[J]. High Voltage Engineering, 2023, 49(7): 2938-2951.
[3] 黄强, 郭怿, 江建华, 等. “双碳”目标下中国清洁电力发展路径[J]. 上海交通大学学报, 2021, 55(12): 1499-1509.
Huang Q, Guo Y, Jiang J H, et al.Development pathway of China’s clean electricity under carbon peaking and carbon neutrality goals[J]. Journal of Shanghai Jiao Tong University, 2021, 55(12): 1499-1509.
[4] 周建国, 周路明, 王剑宇, 等. 基于优化分解与误差修正的光伏发电功率预测[J]. 太阳能学报, 2024, 45(7): 502-509.
Zhou J G, Zhou L M, Wang J Y, et al.PV power forecasting based on optimal decomposition and error correction[J]. Acta Energiae Solaris Sinica, 2024, 45(7): 502-509.
[5] 郭文凯, 王果, 闵永智, 等. 基于FOX-VMD联合小波阈值去噪的短期光伏功率预测研究[J]. 太阳能学报, 2025, 46(6): 260-270.
Guo W K, Wang G, Min Y Z, et al.Research of short-term photovoltaic power prediction based on FOX-VMD combined with wavelet threshold denoising[J]. Acta Energiae Solaris Sinica, 2025, 46(6): 260-270.
[6] 王东风, 李青博, 张博洋, 等. 考虑季节性与趋势特征的光伏功率预测模型研究[J]. 太阳能学报, 2025, 46(3): 348-356.
Wang D F, Li Q B, Zhang B Y, et al.Research on photovoltaic power prediction model considering seasonality and trend characteristics[J]. Acta Energiae Solaris Sinica, 2025, 46(3): 348-356.
[7] 杨晶显, 张帅, 刘继春, 等. 基于VMD和双重注意力机制LSTM的短期光伏功率预测[J]. 电力系统自动化, 2021, 45(3): 174-182.
Yang J X, Zhang S, Liu J C, et al.Short-term photovoltaic power prediction based on variational mode decomposition and long short-term memory with dual-stage attention mechanism[J]. Automation of Electric Power Systems, 2021, 45(3): 174-182.
[8] 刘家庆, 张弘鹏, 郭希海, 等. 基于SVR残差修正的光伏发电功率预测模型[J]. 电力工程技术, 2020, 39(5): 146-151.
Liu J Q, Zhang H P, Guo X H, et al.Prediction model of photovoltaic power generation based on SVR residual correction[J]. Electric Power Engineering Technology, 2020, 39(5): 146-151.
[9] Yona A, Senjyu T, Funabashi T, et al.Determination method of insolation prediction with fuzzy and applying neural network for long-term ahead PV power output correction[J]. IEEE Transactions on Sustainable Energy, 2013, 4(2): 527-533.
[10] 刘大贵, 王维庆, 张慧娥, 等. 基于隐马尔科夫修正的光伏中长期电量预测及调度计划应用[J]. 高电压技术, 2023, 49(2): 840-848.
Liu D G, Wang W Q, Zhang H E, et al.Mid-long term available quantity of electricity forecasting with error calibration by hidden Markov model in photovoltaic and application of dispatching plan[J]. High Voltage Engineering, 2023, 49(2): 840-848.
[11] 宋煜, 许野, 刘锋平, 等. 基于综合相似日选取的SO-CNN-LSTM光伏功率预测模型研究[J]. 太阳能学报, 2025, 46(4): 301-312.
Song Y, Xu Y, Liu F P, et al.Research on SO-CNN-LSTM photovoltaic power prediction model based on comprehensive similar day selection[J]. Acta Energiae Solaris Sinica, 2025, 46(4): 301-312.
[12] 李青. 基于注意力时间卷积神经网络的光伏功率概率预测[J]. 太阳能学报, 2025, 46(2): 326-332.
Li Q.Photovoltaic power probability prediction based on attention time convolutional neural network[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 326-332.
[13] 雷柯松, 吐松江·卡日, 伊力哈木·亚尔买买提, 等. 基于WGAN-GP和CNN-LSTM-Attention的短期光伏功率预测[J]. 电力系统保护与控制, 2023, 51(9): 108-118.
Lei K S, Tusongjiang K, Yilihamu Y, et al.Prediction of short-term photovoltaic power based on WGAN-GP and CNN-LSTM-Attention[J]. Power System Protection and Control, 2023, 51(9): 108-118.
[14] Majumder I, Dash P K, Bisoi R.Variational mode decomposition based low rank robust kernel extreme learning machine for solar irradiation forecasting[J]. Energy Conversion and Management, 2018, 171: 787-806.
[15] 张军. VMD在信号分解中的K值确定方法[J]. 兰州文理学院学报(自然科学版), 2022, 36(4): 75-79.
Zhang J.The K value determination method of VMD in signal decomposition[J]. Journal of Lanzhou University of Arts and Science (Natural Sciences Edition), 2022, 36(4): 75-79.
[16] Sala D A, Van Yperen-De Deyne A, Mannens E, et al. Hybrid-input FCN-CNN-SE for industrial applications: classification of longitudinal cracks during continuous casting[J]. Metals, 2023, 13(10): 1699.
[17] 王玲芝, 李晨阳, 刘婧, 等. 基于GRO-SSA-LSTM的短期光伏发电功率预测[J]. 太阳能学报, 2025, 46(2): 401-409.
Wang L Z, Li C Y, Liu J, et al.Short-term photovoltaic power prediction based on GRO-SSA-LSTM[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 401-409.
[18] 王瑞, 李哲, 逯静. 基于融合聚类和BKA-VMD-TCN-BiLSTM的短期光伏功率预测[J]. 电子科技大学学报, 2025, 54(4): 592-603.
Wang R, Li Z, Lu J.Short-term photovoltaic power forecasting based on fusion clustering and BKA-VMD-TCN-BiLSTM[J]. Journal of University of Electronic Science and Technology of China, 2025, 54(4): 592-603.
[19] 徐恒山, 莫汝乔, 薛飞, 等. 基于时间戳特征提取和CatBoost-LSTM模型的光伏短期发电功率预测[J]. 太阳能学报, 2024, 45(5): 565-575.
Xu H S, Mo R Q, Xue F, et al.Short-term photovoltaic power prediction based on timestamp feature extration and CatBoost-LSTM model[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 565-575.
[20] 滕陈源, 丁逸超, 张有兵, 等. 基于VMD-Informer-BiLSTM模型的超短期光伏功率预测[J]. 高电压技术, 2023, 49(7): 2961-2971.
Teng C Y, Ding Y C, Zhang Y B, et al.Ultra-short-term photovoltaic power prediction based on VMD-informer-BiLSTM model[J]. High Voltage Engineering, 2023, 49(7): 2961-2971.
[21] 吐松江·卡日, 雷柯松, 马小晶, 等. 基于LSTM-Attention和CNN-BiGRU误差修正的光伏功率预测[J]. 太阳能学报, 2024, 45(12): 85-93.
Tusongjiang K, Lei K S, Ma X J, et al.Photovoltaic power prediction based on LSTM-Attention and CNN-BiGRU error correction[J]. Acta Energiae Solaris Sinica, 2024, 45(12): 85-93.