Short-term Photovoltaic Power Forecasting Based on Improved Dung Beetle Optimizer for Optimizing VMD-BiLSTM

NAVIGATE

Table of Contents

STATISTICS

Viewed42

Downloads48

Short-term Photovoltaic Power Forecasting Based on Improved Dung Beetle Optimizer for Optimizing VMD-BiLSTM

PDF下载 (48)

[1]JIANG Jiandong,CHANG Yizhe,XU Chang,et al.Short-term Photovoltaic Power Forecasting Based on Improved Dung Beetle Optimizer for Optimizing VMD-BiLSTM[J].Journal of Zhengzhou University (Engineering Science),2026,47(XX):1-8.[doi:10.13705/j.issn.1671-6833.2025.05.024]

Copy

Journal of Zhengzhou University (Engineering Science)[ISSN 1671-6833/CN 41-1339/T] Volume: 47 Number of periods: 2026 XX Page number: 1-8 Column: Public date: 2026-09-10

Title:: Short-term Photovoltaic Power Forecasting Based on Improved Dung Beetle Optimizer for Optimizing VMD-BiLSTM

Author(s):: JIANG Jiandong¹ ; CHANG Yizhe¹ ; XU Chang¹ ; GUO Jiaqi² ; ZHANG Yichi¹; 1. School of E lectrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China; 2. Anyang Power Supply Company, State Grid Henan Electric Power Company, Anyang 455000, China

Keywords:: photovoltaic power generation; power forecasting; improved dung beetle optimization algorithm; variational mode decomposition; bidirectional long short-term memory

CLC:: TM732

DOI:: 10.13705/j.issn.1671-6833.2025.05.024

Abstract:: In order to improve the accuracy of short-term photovoltaic power forecasting, a model integrating an Improved Dung Beetle Optimizer, Variational Mode Decomposition (VMD), and Bidirectional Long Short-Term Memory (BiLSTM) is proposed. First, a VMD-BiLSTM prediction framework is constructed, where time-series data are decomposed into multiple components via VMD and fed into BiLSTM for individual prediction. The final output is obtained by reconstructing the component-level results to enhance overall prediction performance. Subsequently, to address the tendency of the Dung Beetle Optimizer (DBO) to fall into local optima, an improved DBO algorithm (IDBO) is developed through the introduction of four strategies: Logistic chaotic mapping for initialization, Levy flight for global exploration, golden sine strategy for position updating, and adaptive T-distribution perturbation for local exploitation. Finally, the IDBO was utilized to optimize critical parameters, including the decomposition number K and penalty factor α in VMD, as well as the hidden layer size and Dropout ratio in BiLSTM, thereby enhancing the model’s learning capability and mitigating overfitting. The proposed model was experimentally tested using actual data from photovoltaic power stations in Shandong and Hebei provinces. The results demonstrate that, compared to the unimproved model PBO-VMD-BiLSTM, the proposed model reduces MAE, MAPE, and RMSE by 21.74%, 27.98%, and 21.17% respectively at the Shandong site, and by 22.41%, 45.95%, and 37.38% at the Hebei site.

References:: [1] 史如新, 王德顺, 余涛, 等. 基于 NARX 神经网络-小波分解光伏发电功率预测[J]. 郑州大学学报(工学版), 2020, 41(6): 79-84.
SHI R X, WANG D S, YU T, et al. Prediction of photovoltaic power generation based on NARX neural network-wavelet decomposition[J]. Journal of Zhengzhou University (Engineering Science), 2020, 41(6): 79-84.
[2] MA T, YANG H X, LU L. Solar photovoltaic system modeling and performance prediction[J]. Renewable and Sustainable Energy Reviews, 2014, 36: 304-315.
[3] ALMONACID F, PÉREZ-HIGUERAS P J, FERNÁNDEZ E F, et al. A methodology based on dynamic artificial neural network for short-term forecasting of the power output of a PV generator[J]. Energy Conversion and Management, 2014, 85: 389-398.
[4] ALAM S. Prediction of direct and global solar irradiance using broadband models: Validation of REST model[J]. Renewable Energy, 2006, 31(8): 1253-1263.
[5] LI Y T, SU Y, SHU L J. An ARMAX model for forecasting the power output of a grid connected photovoltaic system[J]. Renewable Energy, 2014, 66: 78-89.
[6] PERSSON C, BACHER P, SHIGA T, et al. Multi-site solar power forecasting using gradient boosted regression trees[J]. Solar Energy, 2017, 150: 423-436.
[7] LUO X, ZHANG D X, ZHU X. Deep learning based forecasting of photovoltaic power generation by incorporating domain knowledge[J]. Energy, 2021, 225: 120240.
[8] PA M, UDDIN M N, REZAEI N. An adaptive neuro-fuzzy model-based algorithm for fault detection in PV systems[J]. IEEE Transactions on Industry Applications, 2024, 60(1): 1919-1927.
[9] 韩晓, 王涛, 韦晓广, 等. 考虑阵列间时空相关性的超短期光伏出力预测[J]. 电力系统保护与控制, 2024, 52(14): 82-94.
HAN X, WANG T, WEI X G, et al. Ultrashort-term photovoltaic output forecasting considering spatiotemporal correlation between arrays[J]. Power System Protection and Control, 2024, 52(14): 82-94.
[10] YANG C, THATTE A A, XIE L. Multitime-scale data-driven spatio-temporal forecast of photovoltaic generation[J]. IEEE Transactions on Sustainable Energy, 2015, 6(1): 104-112.
[11] 方鹏, 高亚栋, 潘国兵, 等. 基于 LSTM 神经网络的中长期光伏发电站发电量预测方法研究[J]. 可再生能源, 2022, 40(1): 48-54.
FANG P, GAO Y D, PAN G B, et al. Research on forecasting method of mid-and long-term photovoltaic generation based on LSTM neural Network[J]. Renewable Energy Resources, 2022, 40(1): 48-54.
[12] LIU W, LIU Y M, FU L, et al. Wind power forecasting method based on bidirectional long-short term memory neural network and error correction[J]. Electric Power Components and Systems, 2021, 49(13/14): 1169-1180.
[13] 王福忠, 王帅峰, 张丽. 基于 VMD-LSTM 与误差补偿的光伏发电超短期功率预测[J]. 太阳能学报, 2022, 43(8): 96-103.
WANG F Z, WANG S F, ZHANG L. Ultra short term power prediction of photovoltaic power generation based on vmd-lstm and error compensation[J]. Acta Energiae Solaris Sinica, 2022, 43(8): 96-103.
[14] 朱菊萍, 魏霞, 谢丽蓉, 等. 基于 VMD 和改进 BiLSTM 的短期风电功率预测[J]. 太阳能学报, 2024, 45(6): 422-428.
ZHU J P, WEI X, XIE L R, et al. Short-term wind power prediction based on vmd and improved BiLSTM[J]. Acta Energiae Solaris Sinica, 2024, 45(6): 422-428.
[15] 刘杰, 从兰美, 夏远祥, 等. 基于 DBO-VMD 和 IWOA-BiLSTM 神经网络组合模型的短期电力负荷预测[J]. 电力系统保护与控制, 2024, 52(8): 123-133.
LIU J, CONG L M, XIA Y X, et al. Short-term power load prediction based on DBO-VMD and an IWOA-BiLSTM neural network combination model[J]. Power System Protection and Control, 2024, 52(8): 123-133.
[16] 汪繁荣, 梅涛, 卢璐. 基于相似日聚类和 VMD-LTWDBO-BiLSTM 的短期光伏功率预测[J]. 智慧电力, 2024, 52(10): 56-63, 111.
WANG F R, MEI T, LU L. Short-term PV power prediction based on similar day clustering with VMD-LTWDBO-BiLSTM[J]. Smart Power, 2024, 52(10): 56-63, 111.
[17] 廖晓辉, 陈川川. 改进的 VMD-HT 在电能质量扰动检测中的应用[J]. 郑州大学学报(工学版), 2021, 42(1): 21-27.
LIAO X H, CHEN C C. Application of improved VMD-HT in power quality disturbance detection[J]. Journal of Zhengzhou University (Engineering Science), 2021, 42(1): 21-27.
[18] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15: 1929-1958.
[19] XUE J K, SHEN B. Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2023, 79(7): 7305-7336.
[20] 彭竑, 陈江旭, 张倩, 等. 多策略改进的蜣螂搜索算法优化 3DDV-Hop 节点定位[J]. 重庆邮电大学学报(自然科学版), 2024, 36(3): 438-449.
PENG D, CHEN J X, ZHANG Q, et al. Optimization of 3DDV-Hop node localization using multi-strategy improved dung beetle search algorithm[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2024, 36(3): 438-449.

Similar References:

Memo

Last Update: 2026-01-15