Linear fitting model for wind power curves based on density correction

doi:10.3969/j.issn.2097-0706.2025.03.008

Abstract

Abstract:

To address the issue that traditional wind power curve models fail to fully consider the effect of meteorological factors， resulting in reduced model accuracy， a new linear fitting model for wind power curves named LI-DASW is proposed with the inclusion of density correction. A calculation model for air density was developed based on meteorological factors such as temperature， pressure， and humidity， as well as a density-corrected wind speed strategy. It reflected the effect of meteorological changes on the wind power curve while maintaining the model's single-input and single-output characteristics. The original dataset was replaced with the first moment to reduce redundant calculations and improve modeling efficiency. A linear interpolation model was constructed using the first moment as interpolation points， effectively avoiding the Runge's phenomenon caused by higher-order polynomial fitting and enhancing the model's adaptability. The case study analysis results of two wind farms demonstrated that the LI-DASW model significantly outperformed traditional methods. Compared to the Bin method， the model's root mean square error（RMSE） reduced by 14.42% and 10.16%， and the mean absolute error（MAE） decreased by 15.63% and 9.48%， respectively. Compared to the polynomial method， the RMSE decreased by 20.33% and 7.66%， and the MAE improved by 18.15% and 8.06%. Compared to the linear interpolation method， the reductions in RMSE and MAE remained stable between 6.19% to 7.37%. Additionally， the modeling efficiency improved by over 84.81% compared to the polynomial model.

Key words: wind power, power curve, linear fitting model, meteorological factors, density-corrected wind speed strategy, first moment, linear interpolation

CLC Number:

TK81

ZHU Dongjie, LYU Kunye, SONG Changhong, JIANG Meihui, LI Zhijiu. Linear fitting model for wind power curves based on density correction[J]. Integrated Intelligent Energy, 2025, 47(3): 84-91.

Figures/Tables 10

Table 1

Table 2

Table 3

Fig.1

Table 4

Table 5

Fig.2

Fig.3

Fig.4

Fig.5

References 27

[1]	TUNCAR A E, SAĞLAM Ş, ORAL B. A review of short-term wind power generation forecasting methods in recent technological trends[J]. Energy Reports, 2024,12:197-209.
[2]	LI Y T, WANG P, WU Z Y, et al. Collaborative monitoring of wind turbine performance based on probabilistic power curve comparison[J]. Renewable Energy, 2024, 231:120919.
[3]	RODRÍGUEZ-LÓPEZ M Á, CERDÁ E, RIO P D. Modeling wind-turbine power curves: Effects of environmental temperature on wind energy generation[J]. Energies, 2020, 13(18):4941.
[4]	张真真. 风电机组功率曲线不达标原因分析及优化措施[J]. 分布式能源, 2021, 6(5): 71-76.
	ZHANG Zhenzhen. Cause analysis and optimization measures for wind turbine substandard power curve[J]. Distributed Energy, 2021, 6(5): 71-76.
[5]	黄哲, 高政南, 杭晨辉, 等. 基于历史运行数据的风电场理论输出功率计算方法分析[J]. 内蒙古电力技术, 2016, 34(6): 1-6.
	HUANG Zhe, GAO Zhengnan, HANG Chenhui, et al. Calculation method analysis of theoretical output power of wind farm based on historical running data[J]. Inner Mongolia Electric Power, 2016, 34(6): 1-6.
[6]	LIN Q C, CAI H L, LIU H W, et al. A novel ultra-short-term wind power prediction model jointly driven by multiple algorithm optimization and adaptive selection[J]. Energy, 2024, 288:129724.
[7]	殷林飞, 蒙雨洁. 基于DenseNet卷积神经网络的短期风电预测方法[J]. 综合智慧能源, 2024, 46(7): 12-20. doi: 10.3969/j.issn.2097-0706.2024.07.002
	YIN Linfei, MENG Yujie. Short-term wind power forecasting based on DenseNet convolutional neural networks[J]. Integrated Intelligent Energy, 2024, 46(7): 12-20. doi: 10.3969/j.issn.2097-0706.2024.07.002
[8]	殷林飞, 仝博文, 李雯吉. 基于多尺度卷积-残差网络的短期风电预测[J/OL]. 综合智慧能源,1-10(2024-09-05)[2024-12-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240904.1013.002.html.
	YIN Linfei, TONG Bowen, LI Wenji. Multiscale convolution-residual network for short-term wind power forecasting[J/OL]. Integrated Intelligent Energy,1-10(2024-09-05)[2024-12-01]. http://kns.cnki.net/kcms/detail/41.1461.TK.20240904.1013.002.html.
[9]	LYDIA M, KUMAR S S, SELVAKUMAR A I, et al. A comprehensive review on wind turbine power curve modeling techniques[J]. Renewable and Sustainable Energy Reviews, 2014, 30:452-460.
[10]	沈小军, 付雪姣. 基于改进光滑样条的风电机组功率曲线建模方法[J]. 高电压技术, 2020, 46(7): 2418-2424.
	SHEN Xiaojun, FU Xuejiao. Modeling of wind turbine power curve based on improved smoothing spline[J]. High Voltage Engineering, 2020, 46(7): 2418-2424.
[11]	WANG Y, HU Q H, SRINIVASAN D, et al. Wind power curve modeling and wind power forecasting with inconsistent data[J]. IEEE Transactions on Sustainable Energy, 2019, 10(1):16-25.
[12]	ÜSTÜNTAŞ T, ŞAHIN A D. Wind turbine power curve estimation based on cluster center fuzzy logic modeling[J]. Journal of Wind Engineering and Industrial Aerodynamics, 2008, 96(5):611-620.
[13]	LÁZARO R, YÜRÜŞEN N Y, MELERO J J. Wind turbine power curve modelling using gaussian mixture copula, ANN regressive and BANN[J]. Journal of physics. Conference Series, 2022, 2265(3):32083.
[14]	KOUISSI M, EN-NAIMI E M, ZOUHAIR A. Hybrid approach for wind turbines power curve modeling founded on multi-agent system and two machine learning algorithms, k-means method and the k-nearest neighbors, in the retrieve phase of the dynamic case based reasoning[J]. International Journal of online and Biomedical Engineering, 2022, 18(6):110-122.
[15]	CAPELLETTI M, RAIMONDO D M, DE NICOLAO G. Wind power curve modeling: A probabilistic Beta regression approach[J]. Renewable Energy, 2024, 223:119970.
[16]	VIRGOLINO G C M, MATTOS C L C, MAGALHÃES J A F, et al. Gaussian processes with logistic mean function for modeling wind turbine power curves[J]. Renewable Energy, 2020, 162:458-465.
[17]	WANG Y, DUAN X, SONG D, et al. Wind power curve modeling with large-scale generalized kernel-based regression model[J]. IEEE Transactions on Sustainable Energy, 2023, 14(4):2121-2132.
[18]	YANG L X, WANG L, ZHANG Z J. Generative wind power curve modeling via machine vision: A deep convolutional network method with data-synthesis-informed-training[J]. IEEE Transactions on Power Systems, 2023, 38(2):1111-1124.
[19]	ZHA W T, JIN Y, SUN Y L, et al. A wind speed vector-wind power curve modeling method based on data denoising algorithm and the improved Transformer[J]. Electric Power Systems Research, 2023, 214:108838.
[20]	PRAANJAL N, AHMED E A. Yaw-adjusted wind power curve modeling: A local regression approach[J]. Renewable Energy, 2023, 202:1368-1376.
[21]	ZHENG Z, YANG L X, ZHANG Z J. Conditional variational autoencoder informed probabilistic wind power curve modeling[J]. IEEE Transactions on Sustainable Energy, 2023, 14(4):2445-2460.
[22]	WEI D X, WANG J Z, LI Z W, et al. Wind power curve modeling with hybrid copula and grey wolf optimization[J]. IEEE Transactions on Sustainable Energy, 2022, 13(1):265-276.
[23]	LIU T H, LYU K Y, CHEN F J, et al. Wind power curve model combining smoothed spline with first-order moments and density-adjusted wind speed strategy[J]. Energy, 2024,313:133628.
[24]	郭军红, 王小萱, 汪月新, 等. Copula分位数回归方法在风电超短期出力预测上的应用[J]. 工程科学学报, 2024, 46(10): 1921-1929.
	GUO Junhong, WANG Xiaoxuan, WANG Yuexin, et al. Enhancing ultra-short-term wind power forecasting using the Copula quantile regression method[J]. Chinese Journal of Engineering, 2024, 46(10): 1921-1929.
[25]	MUSHTAQ K, WARIS A, ZOU R, et al. A comprehensive approach to wind turbine power curve modeling: Addressing outliers and enhancing accuracy[J]. Energy, 2024, 304:131981.
[26]	PICARD A, DAVIS R S, GLÄSER M, et al. Revised formula for the density of moist air (CIPM—2007)[J]. Metrologia, 2008, 45(2):149-155.
[27]	PENG C, WANG J, WU D. Impacts of air density fluctuations toward the mass measurements of a 1 kg silicon sphere[J]. IEEE Access, 2020, 8:140840-140847.

参数	单位	数值
α		1.000 62
β	Pa^-1	3.14×10^-8
γ	K^-2	5.60×10^-7

参数	单位	数值
A	K^-2	1.237 884 7×10^-5
B	K^-1	-1.912 131 6×10^-2
C		33.937 110 47
D	K	-6.343 164 5×10³

参数	单位	数值
a₀	K/Pa	1.581 23×10^-6
a₁	Pa^-1	-2.933 1×10^-8
a₂	K/Pa	1.104 3×10^-10
b₀	K/Pa	5.707 0×10^-6
b₁	Pa^-1	-2.051×10^-8
c₀	K/Pa	1.989 8×10^-4
c₁	Pa^-1	-2.376×10^-6
d	K²/Pa²	1.830×10^-11
e	K²/Pa²	-0.765×10^-8

模型	甲电场		乙电场
模型	RMSE	MAE	RMSE	MAE
Bin	2.757 7	1.603 8	4.613 9	3.166 4
PR	2.962 3	1.653 1	4.487 1	3.117 1
LI	2.515 7	1.448 8	4.456 8	3.094 1
LI-DASW	2.360 0	1.353 1	4.144 9	2.866 0

模型		Bin	PR	LI	LI-DASW
时间复杂度		O(n)	O(nk²)	O(n)	O(n)+O(1)
建模耗时/s	甲电场	0.004	0.098	0.010	0.011
建模耗时/s	乙电场	0.005	0.079	0.010	0.012