SHORT-TERM POWER PREDICTION FOR WIND FARM CLUSTER BASED ON SAMPLE CONVOLUTION INTERACTION NETWORK

Zhu Guopeng; Xiang Ling; Fan Wenzhen; Wu Jun; Li Yuewen; Hu Aijun

doi:10.19912/j.0254-0096.tynxb.2023-1420

PDF(4136 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (1) : 158-167. DOI: 10.19912/j.0254-0096.tynxb.2023-1420

SHORT-TERM POWER PREDICTION FOR WIND FARM CLUSTER BASED ON SAMPLE CONVOLUTION INTERACTION NETWORK

Zhu Guopeng¹, Xiang Ling¹, Fan Wenzhen², Wu Jun², Li Yuewen², Hu Aijun¹

Author information +

History +

Abstract

To ensure the secure and efficient operation of wind farm clusters and optimize regional grid dispatch, a novel methodology for predicting the power output of wind farm clusters based on the Sample Convolution Interaction Network （SCINet） is proposed. The fundamental principles of Energy Entropy （EE） and Variational Mode Decomposition （VMD） to process power sequences with high precision is integrated. Within this predictive framework, the Sample Convolution Interaction Network （SCINet） is employed to forecast stationary sequences, while the Auto Regressive Moving Average （ARMA） model is applied to non-stationary sequences. Subsequently, the outputs of the model are meticulously reconstructed to produce the final prediction results. In the first case study, empirical data from a 150 MW large wind farm located in northeast China are utilized for model development and comprehensive prediction analysis. The results demonstrate the significant advantage of the proposed model in effectively extracting distinctive features from power sequences, thus substantiating its superior predictive accuracy. In the second case study, the methodology is validated using power data from a 298.5 MW wind farm cluster in northwestern China. The validation results affirm the model's robust generalization capability. Compared to conventional methods commonly used for wind farm cluster power prediction, the proposed approach not only outperforms existing methods but also exhibits enhanced computational efficiency. Consequently, it provides a valuable reference for accurate power prediction in similar wind farm clusters.

Key words

wind power / prediction / wind farms / signal processing / variational mode decomposition / convolution

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Zhu Guopeng, Xiang Ling, Fan Wenzhen, Wu Jun, Li Yuewen, Hu Aijun. SHORT-TERM POWER PREDICTION FOR WIND FARM CLUSTER BASED ON SAMPLE CONVOLUTION INTERACTION NETWORK[J]. Acta Energiae Solaris Sinica. 2025, 46(1): 158-167 https://doi.org/10.19912/j.0254-0096.tynxb.2023-1420

References

[1] 张世界, 魏静, 汤宝平, 等. 基于变系数滑模控制器的风电机组振动主动控制研究[J]. 太阳能学报, 2023, 44(5): 407-415.
ZHANG S J, WEI J, TANG B P, et al.Research on vibration control of wind turbines based on variable coefficient sliding mode controller[J]. Acta energiae solaris sinica, 2023, 44(5): 407-415.
[2] 向玲, 刘佳宁, 苏浩, 等. 基于CEEMDAN二次分解和LSTM的风速多步预测研究[J]. 太阳能学报, 2022, 43(8): 334-339.
XIANG L, LIU J N, SU H, et al.Research on multi-step wind speed forecast based on CEEMDAN secondary decomposition and LSTM[J]. Acta energiae solaris sinica, 2022, 43(8): 334-339.
[3] WANG J N, ZHU H Q, CHENG F, et al.A novel wind power prediction model improved with feature enhancement and autoregressive error compensation[J]. Journal of cleaner production, 2023, 420: 138386.
[4] GENG D H, WANG B, GAO Q.A hybrid photovoltaic/wind power prediction model based on Time2Vec, WDCNN and BiLSTM[J]. Energy conversion and management, 2023, 291: 117342.
[5] ABOU HOURAN M, SALMAN BUKHARI S M, ZAFAR M H, et al. COA-CNN-LSTM: coati optimization algorithm-based hybrid deep learning model for PV/wind power forecasting in smart grid applications[J]. Applied energy, 2023, 349: 121638.
[6] 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.
[7] LIANG T, ZHAO Q, LV Q Z, et al.A novel wind speed prediction strategy based on Bi-LSTM, MOOFADA and transfer learning for centralized control centers[J]. Energy, 2021, 230: 120904.
[8] OLIVEIRA SANTOS V, COSTA ROCHA P A, SCOTT J, et al. Spatiotemporal analysis of bidimensional wind speed forecasting: development and thorough assessment of LSTM and ensemble graph neural networks on the Dutch database[J]. Energy, 2023, 278: 127852.
[9] 苏连成, 朱娇娇, 李英伟. 基于时间卷积网络残差校正的短期风电功率预测[J]. 太阳能学报, 2023, 44(7): 427-435.
SU L C, ZHU J J, LI Y W.Short-term wind power prediction based on temporal convolutional network residual correction model[J]. Acta energiae solaris sinica, 2023, 44(7): 427-435.
[10] 毕贵红, 黄泽, 赵四洪, 等. 基于混合分解和PCG-BiLSTM的风速短期预测[J]. 太阳能学报, 2024, 45(1): 159-170.
BI G H, HUANG Z, ZHAO S H, et al.Short-term prediction of wind speed based on hybrid decomposition and PCG-BiLSTM[J]. Acta energiae solaris sinica, 2024, 45(1): 159-170.
[11] 杨丽薇, 高晓清, 蒋俊霞, 等. 基于小波变换与神经网络的光伏电站短期功率预测[J]. 太阳能学报, 2020, 41(7): 152-157.
YANG L W, GAO X Q, JIANG J X, et al.Short-term photovoltaic output power prediction based on wavelet transform and neural network[J]. Acta energiae solaris sinica, 2020, 41(7): 152-157.
[12] 张亚刚, 赵云鹏, 王思祺. 基于EVMD和布谷鸟算法的短期风功率区间预测[J]. 太阳能学报, 2022, 43(8): 292-299.
ZHANG Y G, ZHAO Y P, WANG S Q.Short term wind power interval prediction based on EVMD and cuckoo algorithm[J]. Acta energiae solaris sinica, 2022, 43(8): 292-299.
[13] 刘栋, 魏霞, 王维庆, 等. 基于VMD-WPE和SSA-ELM的短期风电功率预测研究[J]. 太阳能学报, 2022, 43(12): 360-367.
LIU D, WEI X, WANG W Q, et al.Short term wind power forecasting based on VMD-WPE and SSA-ELM[J]. Acta energiae solaris sinica, 2022, 43(12): 360-367.
[14] SUN Z X, ZHAO M Y, ZHAO G H.Hybrid model based on VMD decomposition, clustering analysis, long short memory network, ensemble learning and error complementation for short-term wind speed forecasting assisted by Flink platform[J]. Energy, 2022, 261: 125248.
[15] DRAGOMIRETSKIY K, ZOSSO D.Variational mode decomposition[J]. IEEE transactions on signal processing, 2014, 62(3): 531-544.
[16] ZHENG H, HU Z D, WANG X G, et al.VMD-CAT: a hybrid model for short-term wind power prediction[J]. Energy reports, 2023, 9: 199-211.
[17] WANG L W, LEE C Y, TU Z, et al. Training deeper convolutional networks with deep supervision[J]. Arxiv preprint arxiv:1505.02496, 2015.
[18] 左秀霞. 单位根检验的理论及应用研究[D]. 武汉: 华中科技大学, 2012.
ZUO X X.Research on the theory and application of unit root test[D]. Wuhan: Huazhong University of Science and Technology, 2012.
[19] LIU M, ZENG A, LAI Q, et al.Time series is a special sequence: forecasting with sample convolution and Interaction[C]//Thirty-sixth Conference on Neural Information Processing Systems. New Orleans, United States, 2022.