WIND POWER INTERVAL PREDICTION BASED ON BICAMTCN AND FGFORMER

Tian Xiaodong; Zhang Fei; Ren Xiaoying; Gao Lu; Li Jingtao

doi:10.19912/j.0254-0096.tynxb.2025-1134

PDF(2055 KB)

Acta Energiae Solaris Sinica ›› 2026, Vol. 47 ›› Issue (12) : 432-442. DOI: 10.19912/j.0254-0096.tynxb.2025-1134

WIND POWER INTERVAL PREDICTION BASED ON BICAMTCN AND FGFORMER

Tian Xiaodong, Zhang Fei, Ren Xiaoying, Gao Lu, Li Jingtao

Author information +

History +

Abstract

To improve prediction accuracy and address the limitations of point forecasts in capturing the uncertainty of wind power, this paper proposes a novel integrated forecasting model that combines a bidirectional convolutional attention mechanism-based temporal convolutional network （BiCAMTCN） with a Fourier-gated Transformer （Fgformer）. The BiCAMTCN module first performs hierarchical feature extraction on input wind power sequences. Its bidirectional architecture captures both forward and backward temporal dependencies, while its convolutional attention mechanism adaptively models interdependencies among multiple meteorological variables. The Fgformer module replaces the standard multi-head self-attention mechanism in Transformers with Fourier transform operations to enable efficient frequency-domain modeling. In addition, a residual gating mechanism is introduced to suppress redundant information instead of using plain residual connections. Finally, quantile regression is incorporated to produce interval forecasts at multiple confidence levels. Experimental results demonstrate that the proposed model performs well in both point forecasting and interval forecasting tasks.

Key words

wind power / forecasting / deep learning / temporal convolutional network / Transformer / quantile regression

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Tian Xiaodong, Zhang Fei, Ren Xiaoying, Gao Lu, Li Jingtao. WIND POWER INTERVAL PREDICTION BASED ON BICAMTCN AND FGFORMER[J]. Acta Energiae Solaris Sinica. 2026, 47(12): 432-442 https://doi.org/10.19912/j.0254-0096.tynxb.2025-1134

References

[1] 徐武,范鑫豪,沈智方,等. 多尺度特征提取的Transformer短期风电功率预测[J]. 太阳能学报, 2025, 46(2): 640-648.
Xu W, Fan X H, Shen Z F, et al.Short-term wind power prediction using Transformer with multi-scale feature extraction[J]. Acta Energiae Solaris Sinica, 2025, 46(2): 640-648.
[2] 潘鹏程, 张帅, 刘晖, 等. 基于CAWR-LSTM-TRF模型的超短期风电功率预测[J]. 太阳能学报, 2026, 47(3): 452-461.
Pan P C, Zhang S, Liu H, et al.Ultra-short-term wind power forecasting based on CAWR-LSTM-TRF model[J]. Acta Energiae Solaris Sinica, 2026, 47(3): 452-461.
[3] Hodge B M, Brancucci Martinez-Anido C, Wang Q, et al. The combined value of wind and solar power forecasting improvements and electricity storage[J]. Applied Energy, 2018, 214: 1-15.
[4] 范竞敏, 贺广林, 王新刚, 等. 基于VMD-TCN-GRU-AM的超短期风电预测[J]. 太阳能学报, 2025, 46(6):538-547.
Fan J M, He G L, Wang X G, et al.Ultra-short-term wind power forecasting based on VMD-TCN-GRU-AM[J]. Acta Energiae Solaris Sinica, 2025, 46(6): 538-547.
[5] Xia M, Shao H D, Ma X D, et al.A stacked GRU-RNN-based approach for predicting renewable energy and electricity load for smart grid operation[J]. IEEE Transactions on Industrial Informatics, 2021, 17(10): 7050-7059.
[6] 苏向敬,程子凡,聂良钊,等. 基于AGCN-LSTM模型的海上风电场功率概率预测[J]. 电力系统自动化, 2024, 48(22): 140-149.
Su X J, Cheng Z F, Nie L Z, et al.Power probability prediction for offshore wind farm based on AGCN-LSTM model[J]. Automation of Electric Power Systems, 2024, 48(22): 140-149.
[7] Zhao Z N, Yun S N, Jia L Y, et al.Hybrid VMD-CNN-GRU-based model for short-term forecasting of wind power considering spatio-temporal features[J]. Engineering Applications of Artificial Intelligence, 2023, 121: 105982.
[8] 王莲, 简子淋, 张晓斌, 等. 基于CNN-BiLSTM和多目标函数优化的省级光伏日内保障出力预测[J]. 高电压技术, 2025, 51(9): 4846-4855.
Wang L, Jian Z L, Zhang X B, et al.Intra-day guaranteed power output forecasting for provincial PV systems based on CNN-BiLSTM and multi-objective function optimization[J]. High Voltage Engineering, 2025, 51(9): 4846-4855.
[9] Lin W H, Wang P, Chao K M, et al.Wind power forecasting with deep learning networks: time-series forecasting[J]. Applied Sciences, 2021, 11(21): 10335.
[10] Ewees A A, Al-qaness M A A, Abualigah L, et al. HBO-LSTM: optimized long short term memory with heap-based optimizer for wind power forecasting[J]. Energy Conversion and Management, 2022, 268: 116022.
[11] Wu Q Y, Guan F, Lv C, et al.Ultra-short-term multi-step wind power forecasting based on CNN-LSTM[J]. IET Renewable Power Generation, 2021, 15(5): 1019-1029.
[12] Qu K, Si G Q, Shan Z H, et al.Short-term forecasting for multiple wind farms based on transformer model[J]. Energy Reports, 2022, 8: 483-490.
[13] Wei H, Wang W S, Kao X X.A novel approach to ultra-short-term wind power prediction based on feature engineering and informer[J]. Energy Reports, 2023, 9: 1236-1250.
[14] Gong M J, Yan C C, Xu W, et al.Short-term wind power forecasting model based on temporal convolutional network and Informer[J]. Energy, 2023, 283: 129171.
[15] Peng X S, Wang H Y, Lang J X, et al.EALSTM-QR: Interval wind-power prediction model based on numerical weather prediction and deep learning[J]. Energy, 2021, 220: 119692.
[16] 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.
[17] Iaconis J, Johri S, Zhu E Y.Quantum state preparation of normal distributions using matrix product states[J]. NPJ Quantum Information, 2024, 10: 15.
[18] 韩丽, 乔妍, 景惠甜. 基于误差分类的风电功率区间评估[J]. 电力系统自动化, 2021, 45(1): 97-104.
Han L, Qiao Y, Jing H T.Interval estimation of wind power based on error classification[J]. Automation of Electric Power Systems, 2021, 45(1): 97-104.
[19] 王晓东,鞠邦国,刘颖明,等. 基于QR-NFGLSTM与核密度估计的风电功率概率预测[J].太阳能学报, 2022, 43(2): 479-485.
Wang X D, Ju B G, Liu Y M, et al.Probability prediction of wind power based on QR-NFGLSTM and kernel density estimation[J]. Acta Energiae Solaris Sinica, 2022, 43(2): 479-485.
[20] 王开艳, 杜浩东, 贾嵘,等. 基于相似日聚类和QR-CNN-BiLSTM模型的光伏功率短期区间概率预测[J]. 高电压技术, 2022, 48(11): 4372-4384.
Wang K Y, Du H D, Jia R, et al.Short-term interval probability prediction of photovoltaic power based on similar daily clustering and QR-CNN-BiLSTM model[J]. High Voltage Engineering, 2022, 48(11): 4372-4384.
[21] Lee-Thorp J, Ainslie J, Eckstein I, et al. Fnet: mixing tokens with fourier transforms[PP/OL]. arXiv(2021-05-10)[2025-06-07]. https://arxiv.org/abs/2105.03824.