Study on Wind Power Prediction Based on Wake Effect and Machine Learning

doi:10.3969/j.issn.1008-0198.2023.03.008

Abstract

Abstract: In response to the problem of severely overestimating wind speed loss in the wake zone when using the Jensen wake analysis model to analyze wake effects without considering the additional turbulence intensity brought by upstream fans on downstream wind speed recovery, a Gaussian wake model is proposed to consider wake effects and combine it with machine learning algorithms to improve existing short-term wind power prediction methods based on physical effects. This theoretically improves the accuracy of short-term wind power prediction models in predicting wind speed in the wake region. Experiments are conducted using historical wind power data from real wind farms, and the results show that compared to not considering wake effects, the model's prediction performance had a mean square error reduction of about 15%,and compared with the Jensen wake analysis model, the model's prediction performance had a mean square error reduction of about 7%.

Key words: wake effect, machine learning, wind power prediction, Gaussian wake analysis model

CLC Number:

TM614

YU Zhongze, LIU Zhenqing, MA Chi. Study on Wind Power Prediction Based on Wake Effect and Machine Learning[J]. Hunan Electric Power, 2023, 43(3): 53-59.

References

[1]中国电力企业联合会. 中国电力行业年度发展报告-2019[M]. 北京:中国建材工业出版社,2019.
[2]杨楚原, 姚俊伟, 项川, 等. 面向增量配电网的协同规划方法研究[J]. 湖南电力, 2022, 42(6): 69-75.
[3]Yang Qiuling, Deng Changhong, Chang Xiqiang. Ultra-short-term/short-term wind speed prediction based on improved singular spectrum analysis[J]. Renewable Energy, 2022, 184: 36-44.
[4]Xiaoxun Z, Zixu X, Yu W, et al. Research on wind speed behavior prediction method based on multi-feature and multi-scale integrated learning[J]. Energy, 2023, 263: 125593.
[5]Zhao X, Bai M, Yang X, et al. Short-term probabilistic predictions of wind multi-parameter based on one-dimensional convolutional neural network with attention mechanism and multivariate copula distribution estimation[J]. Energy, 2021,234:121306.
[6]Han Y, Mi L, Shen L, et al. A short-term wind speed prediction method utilizing novel hybrid deep learning algorithms to correct numerical weather forecasting[J]. Applied Energy, 2022, 312: 118777.
[7]Wang F, Tong S, Sun Y, et al. Wind process pattern forecasting based ultra-short-term wind speed hybrid prediction[J]. Energy, 2022, 255: 124509.
[8]Ma Z, Mei G. A hybrid attention-based deep learning approach for wind power prediction[J]. Applied Energy, 2022, 323: 119608.
[9]Shan J, Wang H, Pei G, et al. Research on short-term power prediction of wind power generation based on WT-CABC-KELM[J]. Energy Reports, 2022, 8: 800-809.
[10]Yu G, Liu C, Tang B, et al. Short term wind power prediction for regional wind farms based on spatial-temporal characteristic distribution[J]. Renewable Energy, 2022, 199: 599-612.
[11]Wang H, Ye J, Huang L, et al. A multivariable hybrid prediction model of offshore wind power based on multi-stage optimization and reconstruction prediction[J]. Energy, 2023, 262: 125428.
[12]Zhang W, Lin Z, Liu X. Short-term offshore wind power forecasting-A hybrid model based on Discrete Wavelet Transform (DWT), Seasonal Autoregressive Integrated Moving Average (SARIMA), and deep-learning-based Long Short-Term Memory (LSTM)[J]. Renewable Energy, 2022, 185: 611-628.
[13]Khazaei S, Ehsan M, Soleymani S, et al. A high-accuracy hybrid method for short-term wind power forecasting[J]. Energy, 2022, 238: 122020.
[14]Ye L, Dai B, Li Z, et al. An ensemble method for short-term wind power prediction considering error correction strategy[J]. Applied Energy, 2022, 322: 119475.
[15]Zhang J, Liu D, Li Z, et al. Power prediction of a wind farm cluster based on spatiotemporal correlations[J]. Applied Energy, 2021, 302: 117568.
[16] Farah S, Humaira N, Aneela Z, 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.
[17]Guo N Z, Shi K Z, Li B, et al. A physics-inspired neural network model for short-term wind power prediction considering wake effects[J]. Energy, 2022, 261: 125208.
[18]Qian G W, Takeshi I. A New Analytical Wake Model for Yawed Wind Turbines[J]. Energies,2018,11(3):665.
[19]Ishihara T, Qian G W. A new Gaussian-based analytical wake model for wind turbines considering ambient turbulence intensities and thrust coefficient effects[J]. Journal of Wind Engineering & Industrial Aerodynamics, 2018, 177: 275-292.
[20]Liu Z, Peng J, Hua X, et al. Wind farm optimization considering non-uniformly distributed turbulence intensity[J]. Sustainable Energy Technologies and Assessments, 2021, 43: 100970.