WIND POWER PREDICTION BASED ON IMPROVED INFORMER AND TRANSFER LEARNING

Guo Lijin; Sun Miao; Heng Anyang

doi:10.19912/j.0254-0096.tynxb.2024-0425

PDF(1932 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (7) : 371-377. DOI: 10.19912/j.0254-0096.tynxb.2024-0425

Special Topics of Academic Papers at the 64th Annual Meeting of the China Association for Science and Technology

WIND POWER PREDICTION BASED ON IMPROVED INFORMER AND TRANSFER LEARNING

Guo Lijin^1,2, Sun Miao^1,2, Heng Anyang^1,2

Author information +

History +

Abstract

To overcome the instability of wind power sequences resulting in low prediction accuracy and the limited historical data of some wind farms, we propose a wind power prediction model called feature interaction in Informer with transfer learning （FIITL）. Firstly, we introduce a feature interaction （FI） amechanism with dual-channel input to further extract information. Secondly, transfer learning （TL） is incorporated into the prediction model, resulting in a cyclic fine-tuning transfer learning method. This method transfers the model from a source monitoring station to a target station, thereby improving predictive performance under limited historical data. Finally, the FIITL model is compared with traditional Informer models and other baseline prediction methods. The results demonstrate that the FIITL model outperforms these models in situations with limited data.

Key words

transfer learning / wind power / forecasting / Informer / feature interaction

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Guo Lijin, Sun Miao, Heng Anyang. WIND POWER PREDICTION BASED ON IMPROVED INFORMER AND TRANSFER LEARNING[J]. Acta Energiae Solaris Sinica. 2025, 46(7): 371-377 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0425

References

[1] LIU H, MI X W, LI Y F.Smart deep learning based wind speed prediction model using wavelet packet decomposition, convolutional neural network and convolutional long short term memory network[J]. Energy conversion and management, 2018, 166: 120-131.
[2] SHOKRI GAZAFROUDI A.Assessing the impact of load and renewable energies’ uncertainty on a hybrid system[J]. International journal of energy and power engineering, 2016, 5(2): 1-8.
[3] 张晓艳, 向勉, 朱黎, 等. 基于MLP-BiLSTM-TCN组合的超短期风电功率预测[J]. 湖北民族大学学报(自然科学版), 2023, 41(4): 513-519, 529.
ZHANG X Y, XIANG M, ZHU L, et al.Ultra short term wind power prediction based on MLP-BiLSTM-TCN combination[J]. Journal of Hubei Minzu University (natural science edition), 2023, 41(4): 513-519, 529.
[4] 刘凡, 李捍东, 覃涛. 基于CEEMDAN-AsyHyperBand-MultiTCN的短期风电功率预测[J]. 太阳能学报, 2024, 45(1): 151-158.
LIU F, LI H D, QIN T.Short-term wind power prediction based on CEEMDAN-AsyHyperBand-MultiTCN[J]. Acta energiae solaris sinica, 2024, 45(1): 151-158.
[5] 师洪涛, 李艺萱, 丁茂生, 等. 基于多重联合概率与改进加权HMM的风电功率预测方法[J]. 太阳能学报, 2023, 44(11): 247-254.
SHI H T, LI Y X, DING M S, et al.Wind power prediction method based on multiple joint probability and improved weighted HMM[J]. Acta energiae solaris sinica, 2023, 44(11): 247-254.
[6] 张惠娟, 刘琪, 岑泽尧, 等. 基于GWO-MLP的光伏系统输出功率短期预测模型[J]. 电测与仪表, 2022, 59(7): 72-77, 113.
ZHANG H J, LIU Q, CEN Z Y, et al.Short-term prediction model of output power of photovoltaic system based on GWO-MLP[J]. Electrical measurement & instrumentation, 2022, 59(7): 72-77, 113.
[7] LIU E J, WANG Y X, HUANG Y Z.Short-term forecast of multi-load of electrical heating and cooling in regional integrated energy system based on deep LSTM RNN[C]//2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2). Wuhan, China, 2020: 2994-2998.
[8] HONG Y Y, SATRIANI T R A. Day-ahead spatiotemporal wind speed forecasting using robust design-based deep learning neural network[J]. Energy, 2020, 209: 118441.
[9] 王维高, 魏云冰, 滕旭东. 基于VMD-SSA-LSSVM的短期风电预测[J]. 太阳能学报, 2023, 44(3): 204-211.
WANG W G, WEI Y B, TENG X D.Short-term wind power forecasting based on VMD-SSA-LSSVM[J]. Acta energiae solaris sinica, 2023, 44(3): 204-211.
[10] ZHOU H Y, ZHANG S H, PENG J Q, et al.Informer: beyond efficient transformer for long sequence time-series forecasting[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(12): 11106-11115.
[11] ZHANG Y H, YAN J C.Crossformer: transformer utilizing cross-dimension dependency for multivariate time series forecasting[C] //International Conference on Learning Representations. Kigali, Rwanda ,2024
[12] WU H X, XU J H, WANG J M, et al.Autoformer: decomposition transformers with auto-correlation for long-term series forecasting[J]. Advances in neural information processing systems, 2021, 34: 22419-22430.
[13] ZHOU T, MA Z Q, WEN Q S, et al.FEDformer: frequency enhanced decomposed transformer for long-term series forecasting[C]//International Conference on Machine Learning. Honolulu, Hawaii, USA, 2022: 27268-27286.
[14] MINAMI S, LIU S, WU S, et al.A general class of transfer learning regression without implementation cost[J]. Proceedings of the AAAI conference on artificial intelligence, 2021, 35(10): 8992-8999.
[15] YE R, DAI Q.A relationship-aligned transfer learning algorithm for time series forecasting[J]. Information sciences, 2022, 593: 17-34.
[16] LYU M Q, LI Y F, CHEN L, et al.Air quality estimation by exploiting terrain features and multi-view transfer semi-supervised regression[J]. Information sciences, 2019, 483: 82-95.
[17] MA J, LI Z, CHENG J C P, et al. Air quality prediction at new stations using spatially transferred bi-directional long short-term memory network[J]. Science of the total environment, 2020, 705: 135771.
[18] WOO G, LIU C H, SAHOO D, et al. ETSformer: exponential smoothing transformers for time-series forecasting[EB/OL]. (2022-06-20): 2202.01381. https://arxiv.org/abs/2202.01381v2.
[19] 周军, 王渴心, 王岩. 融合迁移学习与CGAN的风电集群功率超短期预测[J]. 电力系统及其自动化学报, 2024, 36(5): 9-18.
ZHOU J, WANG K X, WANG Y.Fusion of transfer learning and CGAN for ultra short-term power prediction of wind power clusters[J]. Proceedings of the CSU-EPSA, 2024, 36(5): 9-18.
[20] 周姿含, 王叙萌, 陈为. 基于迁移学习的交互时序数据可视化生成方法[J]. 浙江大学学报(工学版), 2024, 58(2): 239-246.
ZHOU Z H, WANG X M, CHEN W.Interactive visualization generation method for time series data based on transfer learning[J]. Journal of Zhejiang University (engineering science), 2024, 58(2): 239-246.