针对现有风电功率预测方法对于风电功率波动信息提取不足与演化规律分析不充分导致性能受限的问题,提出一种基于波动延续场景辨识的超短期风电功率预测方法。首先,研究多湍流过程共同作用下的风电功率波动耦合机制,将历史风电功率动态解耦为多个非线性与线性波动分量的组合形式。然后,引入波动延续性概念,基于非线性与线性解耦参数推导风电功率波动的未来延续尺度,据此划分波动延续场景。同时,构建面向高维稀疏特征的稀疏神经网络（SNN）,辨识历史风电功率的波动延续场景,针对不同场景,分类开展超短期功率预测。最后,依托3处风电场实测风速、功率数据进行算例验证。实验结果表明,以所提模型为基准,相较于各对比模型,所提模型的均方根误差（RMSE）、平均绝对误差（MAE）与平均绝对百分比误差（MAPE）分别至少提升1.46%、2.44%与14.67%,证明其在准确性与稳定性方面更具优势。
Abstract
Addressing the limitations of existing wind power forecasting methods, which arise from insufficient extraction of wind power fluctuation information and inadequate analysis of evolutionary patterns, this paper proposes an ultra-short-term wind power forecasting method based on fluctuation continuation scenario identification. First, the coupling mechanism of wind power fluctuations under multiple turbulent processes is investigated, and historical power data are dynamically decoupled into combined nonlinear and linear fluctuation components. The concept of fluctuation extensibility is then introduced to quantify the future persistence scale of wind power fluctuations, which is derived from nonlinear and linear decoupling parameters, based on which fluctuation-extensibility scenarios are defined. Furthermore, a sparse neural network （SNN） tailored for high-dimensional sparse features is developed to identify fluctuation-continuation scenarios of historical wind power data and perform scenario-based ultra-short-term power forecasting. Finally, experiments are conducted on measured wind speed and power data from three wind farms. The results show that, compared with the benchmark models, the proposed method reduces the root mean square error （RMSE）, mean absolute error （MAE）, and mean absolute percentage error （MAPE） by at least 1.46%, 2.44%, and 14.67%, respectively, which verifies its superior predictive accuracy and stability.
关键词
风电场 /
神经网络 /
发电 /
特征抽取 /
风电功率预测
Key words
wind farm /
neural networks /
power generation /
feature extraction /
wind power forecasting
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 杨勇平, 陈衡, 郝俊红, 等. “双碳”目标下我国燃煤发电转型升级发展路径[J]. 中国电机工程学报, 2024, 44(17): 6900-6910.
Yang Y P, Chen H, Hao J H, et al.Development pathways for the transformation and upgrading of China’s coal-fired power generation under the goals of carbon peak and carbon neutrality[J]. Proceedings of the CSEE, 2024, 44(17): 6900-6910.
[2] 余光正, 陆柳, 汤波, 等. 考虑转折性天气的海上风电功率超短期分段预测方法研究[J]. 中国电机工程学报, 2022, 42(13): 4859-4870.
Yu G Z, Lu L, Tang B, et al.Research on ultra-short-term subsection forecasting method of offshore wind power considering transitional weather[J]. Proceedings of the CSEE, 2022, 42(13): 4859-4870.
[3] 兰昆, 吴战波, 赵泽妮, 等. 基于多因子的太阳辐照度预测方法研究进展[J]. 太阳能学报, 2024, 45(5): 593-601.
Lan K, Wu Z B, Zhao Z N, et al.Advance in prediction methods for solar irradiance based on multiple-factors[J]. Acta Energiae Solaris Sinica, 2024, 45(5): 593-601.
[4] 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.
[5] 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.
[6] Zhen Z, Qiu G, Mei S W, et al.An ultra-short-term wind speed forecasting model based on time scale recognition and dynamic adaptive modeling[J]. International journal of electrical power & energy systems, 2022, 135: 107502.
[7] Fan H J, Zhen Z, Liu N, et al.Fluctuation pattern recognition based ultra-short-term wind power probabilistic forecasting method[J]. Energy, 2023, 266: 126420.
[8] Wang F, Tong S, Sun Y Q, et al.Wind process pattern forecasting based ultra-short-term wind speed hybrid prediction[J]. Energy, 2022, 255: 124509.
[9] 胡帅, 向月, 沈晓东, 等. 计及气象因素和风速空间相关性的风电功率预测模型[J]. 电力系统自动化, 2021, 45(7): 28-36.
Hu S, Xiang Y, Shen X D, et al.Wind power prediction model considering meteorological factor and spatial correlation of wind speed[J]. Automation of Electric Power Systems, 2021, 45(7): 28-36.
[10] 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.
[11] 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.
[12] Yang T, Yang Z N, Li F, et al.A short-term wind power forecasting method based on multivariate signal decomposition and variable selection[J]. Applied Energy, 2024, 360: 122759.
[13] Li N, Dong J, Liu L Y, et al.A novel EMD and causal convolutional network integrated with Transformer for ultra short-term wind power forecasting[J]. International Journal of Electrical Power & Energy systems, 2023, 154: 109470.
[14] Meng A B, Chen S, Ou Z H, et al.A hybrid deep learning architecture for wind power prediction based on bi-attention mechanism and crisscross optimization[J]. Energy, 2022, 238: 121795.
[15] Cho M, Hwang Y, Choi H.Scale interactions and spectral energy transfer in turbulent channel flow[J]. Journal of Fluid Mechanics, 2018, 854: 474-504.
[16] Tiwari R, Babu N R.Recent developments of control strategies for wind energy conversion system[J]. Renewable and Sustainable Energy Reviews, 2016, 66: 268-285.
[17] Syed A H, Mann J, Platis A, et al.Turbulence structures and entrainment length scales in large offshore wind farms[J]. Wind Energy Science, 2023, 8(1): 125-139.
[18] 许子非, 邹锦华, 李春, 等. 基于R/S类分析法的风速时间序列Hurst指数分析[J]. 动力工程学报, 2019, 39(7): 585-590, 604.
Xu Z F, Zou J H, Li C, et al.R/S analysis on Hurst exponent of wind speed time series[J]. Journal of Chinese Society of Power Engineering, 2019, 39(7): 585-590, 604.
[19] Tian Z D.Analysis and research on chaotic dynamics behaviour of wind power time series at different time scales[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(2): 897-921.
[20] Leahy P G, McKeogh E J. Persistence of low wind speed conditions and implications for wind power variability[J]. Wind Energy, 2013, 16(4): 575-586.
[21] El Kafrawy P, Fathi H, Qaraad M, et al.An efficient SVM-based feature selection model for cancer classification using high-dimensional microarray data[J]. IEEE Access, 2021, 9: 155353-155369.
[22] Kissane C, Krzyzanowski R, Bloom J I, et al. Interpreting attention layer outputs with sparse autoencoders[PP/OL]. arXiv (2024-06-25)[2026-06-08]. https://doi.org/10.48550/arXiv.2406.17759.
[23] Le V T, Kim Y G.Attention-based residual autoencoder for video anomaly detection[J]. Applied Intelligence, 2023, 53(3): 3240-3254.
[24] Qin Y, Yang J H, Zhou J H, et al.A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL prediction[J]. Advanced Engineering Informatics, 2023, 56: 101973.
[25] Wang L G, Wang X Y, Vizziello A, et al.RSAAE: residual self-attention-based autoencoder for hyperspectral anomaly detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5510614.
[26] Mukherjee S, Singh R K, James M, et al.Intermittency, fluctuations and maximal chaos in an emergent universal state of active turbulence[J]. Nature Physics, 2023, 19(6): 891-897.
[27] Guo C S, Li Y W, Nian X B, et al.Experimental study on the slip velocity of turbulent flow over and within porous media[J]. Physics of Fluids, 2020, 32: 015111.
[28] Hong S, Chung T K, Yoo B S, et al.Innovative LSTM-transformer hybrid models for predicting consolidation settlement[J]. Acta Geotechnica, 2025, 20(10): 5487-5513.
[29] Guo J X, Yun S N, Meng Y, et al.Prediction of heating and cooling loads based on light gradient boosting machine algorithms[J]. Building and Environment, 2023, 236: 110252.
[30] Meng Y, Yun S N, Zhao Z N, et al.Short-term electricity load forecasting based on a novel data preprocessing system and data reconstruction strategy[J]. Journal of Building Engineering, 2023, 77: 107432.
[31] Jia L Y, Yun S N, Zhao Z N, et al.Improving short-term forecasting of solar power generation by using an EEMD-BiGRU model: a comparative study based on seven standalone models and six hybrid models[J]. International Journal of Green Energy, 2024, 21(14): 3135-3158.
PDF(2071 KB)
