基于帝王蝶算法的CNN-GRU-LightGBM模型短期风电功率预测

向阳; 刘亚娟; 孙志伟; 张效宁; 卢建谋

doi:10.19912/j.0254-0096.tynxb.2023-1388

PDF(2452 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (1) : 105-114. DOI: 10.19912/j.0254-0096.tynxb.2023-1388

基于帝王蝶算法的CNN-GRU-LightGBM模型短期风电功率预测

向阳¹, 刘亚娟¹, 孙志伟¹, 张效宁², 卢建谋¹

作者信息 +

SHORT TERM WIND POWER PREDICTION USING CNN-GRU-LightGBM MODEL BASED ON EMPEROR BUTTERFLY ALGORITHM

Xiang Yang¹, Liu Yajuan¹, Sun Zhiwei¹, Zhang Xiaoning², Lu Jianmou¹

Author information +

文章历史 +

摘要

风电集群大规模并网和跨季节使用产生的不确定性对风电功率预测播报的准确度提出更高的要求。为提高风电功率预测的准确度,提出一种基于帝王蝶优化算法（MBO）的卷积神经网络（CNN）-门控循环单元（GRU）-梯度提升学习（LightGBM）复合风电功率预测模型。首先,分别建立CNN-GRU和LightGBM的风电功率预测模型,利用方差倒数法将两个模型加权组合为CNN-GRU-LightGBM复合模型;为优化模型中的连续参数,使用MBO对模型进行超参数优化。最后,选取珠海某海上风电场的短期风电功率数据对所提方法与已有预测方法进行对比,实验结果表明,该模型结合了CNN-GRU、LightGBM等模型的优点,预测误差更小,预测精度更高,拥有更强的季节普适性。

Abstract

Uncertainties arising from large-scale grid integration and cross-seasonal use of wind power clusters place higher demands on the accuracy of wind power prediction. To improve the accuracy of wind power prediction, a Convolutional Neural Networks （CNN） Gated Recurrent Unit （GRU） -LightGBM Gradient Boosting Machine （LightGBM） composite wind power prediction model based on Monarch Butterfly Optimization （MBO） algorithm is proposed. Firstly, establish wind power prediction models for CNN-GRU and LightGBM respectively, and use the reciprocal variance method to weight and combine the two models into a CNN-GRU LightGBM composite model; To optimize the continuous parameters in the model, MBO is used to perform hyperparameter optimization on the model. Finally, short-term wind power data from an offshore wind farm in Zhuhai was selected to compare the proposed method with existing prediction methods. The experimental results showed that the model combined the advantages of models such as CNN-GRU and LightGBM, resulting in smaller prediction errors, higher prediction accuracy, and stronger seasonal universality.

导出引用

向阳, 刘亚娟, 孙志伟, 张效宁, 卢建谋. 基于帝王蝶算法的CNN-GRU-LightGBM模型短期风电功率预测[J]. 太阳能学报. 2025, 46(1): 105-114 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1388

Xiang Yang, Liu Yajuan, Sun Zhiwei, Zhang Xiaoning, Lu Jianmou. SHORT TERM WIND POWER PREDICTION USING CNN-GRU-LightGBM MODEL BASED ON EMPEROR BUTTERFLY ALGORITHM[J]. Acta Energiae Solaris Sinica. 2025, 46(1): 105-114 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1388

中图分类号： TW614

参考文献

[1] 《中国能源发展报告2022》: 我国能源绿色低碳转型加快推进[J]. 经济导刊, 2022(7): 6.
China energy development report2022: accelerating the green and low carbon transformation of energy in China[J]. Economic journal, 2022(7): 6.
[2] 中电建协发布《中国电力建设行业年度发展报告2022》[J]. 中国电力企业管理, 2022(27): 8.
China electric power construction association released the Annual development report of China electric power construction industry2022[J]. China electric power enterprise management, 2022(27): 8.
[3] HOSSAIN M A, CHAKRABORTTY R K, ELSAWAH S, et al.Very short-term forecasting of wind power generation using hybrid deep learning model[J]. Journal of cleaner production, 2021, 296: 126564.
[4] CHEN N Y, QIAN Z, NABNEY I T, et al.Wind power forecasts using Gaussian processes and numerical weather prediction[J]. IEEE transactions on power systems, 2014, 29(2): 656-665.
[5] 查雯婷, 杨帆, 陈波, 等. 基于CNN的区域风功率预测方法[J]. 计算机仿真, 2021, 38(5): 318-323.
ZHA W T, YANG F, CHEN B, et al.A regional wind power prediction method based on CNN[J]. Computer simulation, 2021, 38(5): 318-323.
[6] 李焱, 贾雅君, 李磊, 等. 基于随机森林算法的短期电力负荷预测[J]. 电力系统保护与控制, 2020, 48(21): 117-124.
LI Y, JIA Y J, LI L, et al.Short term power load forecasting based on a stochastic forest algorithm[J]. Power system protection and control, 2020, 48(21): 117-124.
[7] 韩朋, 张晓琳, 张飞, 等. 基于AM-LSTM模型的超短期风电功率预测[J]. 科学技术与工程, 2020, 20(21): 8594-8600.
HAN P, ZHANG X L, ZHANG F, et al.Ultra-short-term wind power prediction based on AM-LSTM model[J]. Science technology and engineering, 2020, 20(21): 8594-8600.
[8] 徐磊, 吴鹏, 徐明生, 等. 基于卷积神经网络与LightGBM的短期风电功率预测方法[J]. 水电能源科学, 2021, 39(2): 209-212, 199.
XU L, WU P, XU M S, et al.Short-term wind power prediction based on convolution neural network and LightGBM algorithm[J]. Water resources and power, 2021, 39(2): 209-212, 199.
[9] 徐岩, 向益锋, 马天祥. 基于粒子群算法优化参数的VMD-GRU短期电力负荷预测模型[J]. 华北电力大学学报(自然科学版), 2023, 50(1): 38-47.
XU Y, XIANG Y F, MA T X.VMD-GRU short-term power load forecasting model based on optimized parameters of partical swarm algorithm[J]. Journal of North China Electric Power University(natural science edition), 2023, 50(1): 38-47.
[10] LING S H, LEUNG F H F, LAM H K, et al. A novel genetic-algorithm-based neural network for short-term load forecasting[J]. IEEE transactions on industrial electronics, 2003, 50(4): 793-799.
[11] WANG G G, ZHAO X C, DEB S.A novel monarch butterfly optimization with greedy strategy and self-adaptive[C]//2015 Second International Conference on Soft Computing and Machine Intelligence (ISCMI). Hong Kong, China, 2015: 45-50.
[12] 赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234.
ZHAO Z N, YUN S N, JIA L Y, et al.Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta energiae solaris sinica, 2022, 43(11): 224-234.
[13] 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 artificial neural networks[J]. Acta energiae solaris sinica, 2022, 43(12): 88-97.
[14] ABEDINIA O, BAGHERI M, NADERI M S, et al.A new combinatory approach for wind power forecasting[J]. IEEE systems journal, 2020, 14(3): 4614-4625.
[15] NIU Z W, YU Z Y, TANG W H, et al.Wind power forecasting using attention-based gated recurrent unit network[J]. Energy, 2020, 196: 117081.
[16] HUAI N N, DONG L, WANG L J, et al.Short-term wind speed prediction based on CNN_GRU model[C]//2019 Chinese Control and Decision Conference (CCDC). Nanchang, China, 2019: 2243-2247.
[17] 张未, 余成波, 王士彬, 等. 基于VMD-LSTM-LightGBM的多特征短期电力负荷预测[J]. 南方电网技术, 2023, 17(2): 74-81.
ZHANG W, YU C B, WANG S B, et al.Multi-featured short-term power load forecasting based on VMD-LSTM-LightGBM[J]. Southern power system technology, 2023, 17(2): 74-81.
[18] 王愈轩, 刘尔佳, 黄永章. 基于CNN-LSTM-lightGBM组合的超短期风电功率预测方法[J]. 科学技术与工程, 2022, 22(36): 16067-16074.
WANG Y X, LIU E J, HUANG Y Z.An ultra-short-term wind power prediction method based on CNN-LSTM-lightGBM combination[J]. Science technology and engineering, 2022, 22(36): 16067-16074.
[19] 闫琳琦, 王振雷. 基于STA-BiLSTM-LightGBM组合模型的多步预测软测量建模[J]. 化工学报, 2023, 74(8): 3407-3418.
YAN L Q, WANG Z L.Multi-step predictive soft sensor modeling based on STA-BiLSTM-LightGBM combined model[J]. CIESC journal, 2023, 74(8): 3407-3418.
[20] HOSSAIN M A, GRAY E M, ISLAM M R, et al.Forecasting very short-term wind power generation using deep learning, optimization and data decomposition techniques[C]//2021 24th International Conference on Electrical Machines and Systems (ICEMS). Gyeongju, Korea, 2021: 323-327.
[21] MONTAHA S, AZAM S, RAFID A K M R H, et al. TimeDistributed-CNN-LSTM: a hybrid approach combining CNN and LSTM to classify brain tumor on 3D MRI scans performing ablation study[J]. IEEE access, 2022, 10: 60039-60059.
[22] WANG Y Y, CHEN J, CHEN X Q, et al.Short-term load forecasting for industrial customers based on TCN-LightGBM[J]. IEEE transactions on power systems, 2021, 36(3): 1984-1997.
[23] 党存禄, 杨海兰, 武文成. 基于LSTM和CatBoost组合模型的短期负荷预测[J]. 电气工程学报, 2021, 16(3): 62-69.
DANG C L, YANG H L, WU W C.Short-term load forecasting based on LSTM and CatBoost combined model[J]. Journal of electrical engineering, 2021, 16(3): 62-69.
[24] HOSSAIN M A, GRAY E, LU J W, et al.Optimized forecasting model to improve the accuracy of very short-term wind power prediction[J]. IEEE transactions on industrial informatics, 2023, 19(10): 10145-10159.
[25] WANG G G, DEB S, CUI Z H.Monarch butterfly optimization[J]. Neural computing and applications, 2019, 31(7): 1995-2014.
[26] LIN Z, LIU X L, COLLU M.Wind power prediction based on high-frequency SCADA data along with isolation forest and deep learning neural networks[J]. International journal of electrical power and energy systems, 2020, 118: 105835.
[27] DENG W, GUO Y X, LIU J, et al.A missing power data filling method based on improved random forest algorithm[J]. Chinese journal of electrical engineering, 2019, 5(4): 33-39.