RESEARCH ON SHORT-TERM WIND POWER HYBRID FORECASTING MODEL BASED ON IMPROVED SVR-SSA-BILSTM ERROR CORRECTION

Wang Shenran; Hu Hao; Wu Zichen; Gu Bin; Ge Wei

doi:10.19912/j.0254-0096.tynxb.2024-1039

PDF(1700 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (10) : 689-695. DOI: 10.19912/j.0254-0096.tynxb.2024-1039

RESEARCH ON SHORT-TERM WIND POWER HYBRID FORECASTING MODEL BASED ON IMPROVED SVR-SSA-BILSTM ERROR CORRECTION

Wang Shenran¹, Hu Hao¹, Wu Zichen¹, Gu Bin¹, Ge Wei²

Author information +

History +

Abstract

In response to the lack of predictive accuracy and error processing of the existing predictive model when dealing with the severe fluctuations of wind power, this work proposes a mixed wind power prediction method based on error -based modification, combining the experience modus of the time -based filter to decompose TVFEMD, TVFEMD, and Support vector return to SVR and two -way long -term memory neural network BiLSTM. First of all, the original wind power data is decomposed into this modulus function IMFS by applying TVFEMD to achieve the purpose of eliminating its complexity and uncertainty. Then, the improved grid search algorithm and cross -verification algorithm （GridsearchCV） optimize the support vector regression model, and use the model to predict the decomposed IMFS. Secondly, use a improved sparrow search algorithm （SSA） to optimize the BiLSTM network construction error correction model, predict the prediction error of support vector regression, and superimpose the prediction results with those of support vector regression to obtain a more accurate final prediction result. This method not only improves the accuracy of wind power prediction, but also provides a more reliable basis for the fields of wind power power generation. Compared with the results of the prediction model constructed under other optimization methods, this model has higher predition accuracy and stability.

Key words

wind power forecasting / empirical mode decomposition / support vector machine / long short-term memory / deep learning

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Wang Shenran, Hu Hao, Wu Zichen, Gu Bin, Ge Wei. RESEARCH ON SHORT-TERM WIND POWER HYBRID FORECASTING MODEL BASED ON IMPROVED SVR-SSA-BILSTM ERROR CORRECTION[J]. Acta Energiae Solaris Sinica. 2025, 46(10): 689-695 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1039

References

[1] 孙英聪, 陈来军, 李笑竹, 等. 考虑资源相关性的新能源场站群集中式共享储能优化配置[J]. 太阳能学报, 2024, 45(7): 2-9.
SUN Y C, CHEN L J, LI X Z, et al.Optimal allocation of centralized shared energy storage for renewable energy station clusters with consideration of resource correlation[J]. Acta energiae solaris sinica, 2024, 45(7): 2-9.
[2] FARAH S, DAVID A W, HUMAIRA N, et al.Short-term multi-hour ahead country-wide wind power prediction for Germany using gated recurrent unit deep learning[J]. Renewable and sustainable energy reviews, 2022, 167: 112700.
[3] 刘兴, 王艳, 纪志成. 基于SA-GAELM的短期风电功率组合预测[J]. 扬州大学学报(自然科学版), 2021, 24(4): 58-63.
LIU X, WANG Y, JI Z C.Short-term wind power combination prediction based on SA-GAELM[J]. Journal of Yangzhou University (natural science edition), 2021, 24(4): 58-63.
[4] PAN X X, WANG L, WANG Z J, et al.Short-term wind speed forecasting based on spatial-temporal graph transformer networks[J]. Energy, 2022, 253: 124095.
[5] 张帅可, 罗萍萍. 基于混合分布模型的风电功率超短期预测误差分析[J]. 电力科学与技术学报, 2020, 35(5): 111-118.
ZHANG S K, LUO P P.Ultra short-time prediction error analysis of wind power based on mixed distribution model[J]. Journal of electric power science and technology, 2020, 35(5): 111-118.
[6] XIONG B R, LOU L, MENG X Y, et al.Short-term wind power forecasting based on Attention mechanism and deep learning[J]. Electric power systems research, 2022, 206: 107776.
[7] LI H J.Short-term wind power prediction via spatial temporal analysis and deep residual networks[J]. Frontiers in energy research, 2022, 10: 920407.
[8] 肖烈禧, 张玉, 周辉, 等. 基于IAOA-VMD-LSTM的超短期风电功率预测[J]. 太阳能学报, 2023, 44(11): 239-246.
XIAO L X, ZHANG Y, ZHOU H, et al.Ultra short trem wind power prediction based on IAOA-VMD-LSTM[J]. Acta energiae solaris sinica, 2023, 44(11): 239-246.
[9] 程先龙, 保佑智, 何度江, 等. 基于EMD-ELM-LSTM的短期风电功率预测[J]. 昆明理工大学学报(自然科学版), 2023, 48(6): 78-87.
CHENG X L, BAO Y Z, HE D J, et al.Short-term wind power prediction based on EMD-ELM-LSTM[J]. Journal of Kunming University of Science and Technology (natural science), 2023, 48(6): 78-87.
[10] 王东风, 李旭昕, 黄宇, 等. 基于时变滤波经验模态分解与时空相关性误差修正的短期风速预测[J/OL]. 华北电力大学学报(自然科学版), 2023: 1-11. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=HBDL20231104003&dbname=CJFD&dbcode=CJFQ.
WANG D F, LI X X, HUANG Y, et al. Short-term wind speed prediction based on time-varying filtered empirical modal decomposition with spatio-temporal correlation error correction[J/OL]. Journal of North China Electric Power University (natural science edition), 2023: 1-11. https://kns.cnki.net/KCMS/detail/detail.aspx?filename=HBDL20231104003&dbname=CJFD&dbcode=CJFQ.
[11] 齐先军, 郑夕炜, 王晓蓉, 等. 基于时频分析的改进小波包风电功率波动平抑方法[J]. 太阳能学报, 2022, 43(7): 302-309.
QI X J, ZHENG X W, WANG X R, et al.Improved wavelet packet method of smoothing wind power fluctuations based on time-frequency analysis[J]. Acta energiae solaris sinica, 2022, 43(7): 302-309.
[12] ZHOU X L, LIN W Y, KUMAR R, et al.A data-driven strategy using long short term memory models and reinforcement learning to predict building electricity consumption[J]. Applied energy, 2022, 306: 118078.
[13] 程凯, 彭小圣, 徐其友, 等. 基于特征选择与多层级深度迁移学习的风电场短期功率预测[J]. 高电压技术, 2022, 48(2): 497-503.
CHENG K, PENG X S, XU Q Y, et al.Short-term wind power prediction based on feature selection and multi-level deep transfer learning[J]. High voltage engineering, 2022, 48(2): 497-503.
[14] 孙骁强, 马晓伟, 张小奇, 等. 基于相依关系的新能源功率预测场景生成及调度应用[J]. 电力系统自动化, 2019, 43(15): 10-17, 41.
SUN X Q, MA X W, ZHANG X Q, et al.Dependence relationship based scenario generation of power prediction for renewable energy and its application in dispatch[J]. Automation of electric power systems, 2019, 43(15): 10-17, 41.
[15] 潘霄, 张明理, 刘德宝, 等. 基于鲁棒多标签生成对抗的风电场日前出力区间预测[J]. 电力系统自动化, 2022, 46(10): 216-223.
PAN X, ZHANG M L, LIU D B, et al.Interval prediction of wind farm day-ahead output based on robust multi-label generative adversarial[J]. Automation of electric power systems, 2022, 46(10): 216-223.
[16] DUAN J D, WANG P, MA W T, et al.A novel hybrid model based on nonlinear weighted combination for short-term wind power forecasting[J]. International journal of electrical power & energy systems, 2022, 134: 107452.
[17] 孙荣富, 张涛, 和青, 等. 风电功率预测关键技术及应用综述[J]. 高电压技术, 2021, 47(4): 1129-1143.
SUN R F, ZHANG T, HE Q, et al.Review on key technologies and applications in wind power forecasting[J]. High voltage engineering, 2021, 47(4): 1129-1143.
[18] 叶林, 赵金龙, 路朋, 等. 考虑气象特征与波动过程关联的短期风电功率组合预测[J]. 电力系统自动化, 2021, 45(4): 54-62.
YE L, ZHAO J L, LU P, et al.Combined prediction of short-term wind power considering correlation of meteorological features and fluctuation process[J]. Automation of electric power systems, 2021, 45(4): 54-62.
[19] 曹正江, 付文龙, 文斌, 等. 基于TVFEMD和多模型融合的变压器油中溶解气体体积分数预测方法[J]. 高压电器, 2024, 60(8): 156-166.
CAO Z J, FU W L, WEN B, et al.Prediction method of dissolved gas volume fraction in transformer oil based on TVFEMD and multi-model fusion[J]. High voltage apparatus, 2024, 60(8): 156-166.
[20] 张婉莹, 何耀耀, 杨善林. 基于TVFEMD-SE和YJQRG的短期风电功率多步概率密度预测[J]. 系统工程理论与实践, 2022, 42(8): 2225-2242.
ZHANG W Y, HE Y Y, YANG S L.Multi-step probability density prediction of short-term wind power based on TVFEMD-SE and YJQRG[J]. Systems engineering-theory & practice, 2022, 42(8): 2225-2242.
[21] XIAN H F, CHE J X.Unified whale optimization algorithm based multi-kernel SVR ensemble learning for wind speed forecasting[J]. Applied soft computing, 2022, 130: 109690.
[22] PIRI J, ABDOLAHIPOUR M, KESHTEGAR B.Advanced machine learning model for prediction of drought indices using hybrid SVR-RSM[J]. Water resources management, 2023, 37(2): 683-712.
[23] SUROOR N, JAISWAL A, SACHDEVA N.Stack ensemble oriented parkinson disease prediction using machine learning approaches utilizing GridSearchCV-based hyper parameter tuning[J]. Critical reviews in biomedical engineering, 2022, 50(5): 39-58.
[24] WOŹNIAK M, WIECZOREK M, SIŁKA J. BiLSTM deep neural network model for imbalanced medical data of IoT systems[J]. Future generation computer systems, 2023, 141: 489-499.
[25] XIONG J L, PENG T, TAO Z H, et al.A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction[J]. Energy, 2023, 266: 126419.