考虑历史相似性加权的超短期风电功率组合预测

仲悟之; 李崇钢; 崔杨; 李芳; 王丹丹

doi:10.19912/j.0254-0096.tynxb.2021-0308

PDF(1889 KB)

太阳能学报 ›› 2022, Vol. 43 ›› Issue (6) : 160-168. DOI: 10.19912/j.0254-0096.tynxb.2021-0308

考虑历史相似性加权的超短期风电功率组合预测

仲悟之¹, 李崇钢², 崔杨², 李芳¹, 王丹丹¹

作者信息 +

COMBINED PREDICTION OF ULTRA-SHORT TERM WIND POWER CONSIDERING WEIGHTED HISTORICAL SIMILARITY

Zhong Wuzhi¹, Li Chonggang², Cui Yang², Li Fang¹, Wang Dandan¹

Author information +

文章历史 +

摘要

提出一种基于历史相似性加权的超短期风电功率组合预测方法。首先,采用数值天气预报数据、风电历史数据分别作为极限学习机、长短期记忆网络的输入特征并产生预测数据;然后,通过加权灰色关联算法提取与待预测点特征近似的历史数据,评估并校正两类预测模型的预测结果。采用美国科罗拉多州某风电场实际运行数据进行训练与验证,并使用不同加权方法进行对比。结果表明,基于历史相似性优化方法可改善预测效果,缩小预测误差分布范围,验证了该文方法的有效性。

Abstract

Accurate and reliable wind power forecasting is of great significance for improving the wind power consumption rate of power systems. Reasonably combining numerical weather forecast data is an effective means to improve the accuracy of wind power forecasting. This paper proposes a method to improve the ultra-short-term prediction accuracy of long- short-term memory networks based on historical similarity. Firstly, the numerical weather forecast is used as the characteristic of the extreme learning machine to generate correction data; then, through the weighted gray correlation algorithm, the historical data that is similar to the feature of the point to be predicted is extracted, and the prediction results of the long-short-term memory network are evaluated and corrected. The calculation example uses the actual operation data of a wind farm in Colorado, USA for training and verification, and uses different correction methods for comparison. The results show that the optimization method based on historical similarity can improve the prediction effect of the short-term memory network and reduce the error fluctuation range, and verified the method in this article.

导出引用

仲悟之, 李崇钢, 崔杨, 李芳, 王丹丹. 考虑历史相似性加权的超短期风电功率组合预测[J]. 太阳能学报. 2022, 43(6): 160-168 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0308

Zhong Wuzhi, Li Chonggang, Cui Yang, Li Fang, Wang Dandan. COMBINED PREDICTION OF ULTRA-SHORT TERM WIND POWER CONSIDERING WEIGHTED HISTORICAL SIMILARITY[J]. Acta Energiae Solaris Sinica. 2022, 43(6): 160-168 https://doi.org/10.19912/j.0254-0096.tynxb.2021-0308

中图分类号： TM743

参考文献

[1] 薛禹胜, 郁琛, 赵俊华, 等. 关于短期及超短期风电功率预测的评述[J]. 电力系统自动化, 2015, 39(6): 141-151.
XUE Y S, YU C, ZHAO J H, et al.A review on short-term and ultra-short-term wind power prediction[J]. Automation of electric power systems, 2015, 39(6): 141-151.
[2] 杨秀媛, 梁贵书. 风力发电的发展及其市场前景[J]. 电网技术, 2003, 27(7): 78-79.
YANG X Y, LIANG G S.Development of wind power generation and its market prospect[J]. Power system technology, 2003, 27(7): 78-79.
[3] 彭小圣, 熊磊, 文劲宇, 等. 风电集群短期及超短期功率预测精度改进方法综述[J]. 中国电机工程学报, 2016, 36(23): 6315-6326, 6596.
PENG X S, XIONG L, WEN J Y, et al.Summary of improved methods for short-term and ultra-short-term power prediction accuracy of wind power clusters[J]. Proceedings of the CSEE, 2016, 36(23): 6315-6326, 6596.
[4] 冯双磊, 王伟胜, 刘纯, 等. 风电场功率预测物理方法研究[J]. 中国电机工程学报, 2010, 30(2): 1-6.
FENG S L, WANG W S, LIU C, et al.Research on physical method of wind farm power prediction[J]. Proceedings of the CSEE, 2010, 30(2): 1-6.
[5] ZHAO J, GUO Z H, SU Z Y, et al.An improved multi-step forecasting model based on WRF ensembles and creative fuzzy systems for wind speed[J]. Applied energy, 2016, 162(15): 808-826.
[6] ZAMEER A, ARSHAD J, KHAN A, et al.Intelligent and robust prediction of short term wind power using genetic programming based ensemble of neural networks[J]. Energy conversion and management, 2017, 134(2): 361-372.
[7] 肖逸, 李程煌, 刘若平, 等. 基于风速局部爬坡误差校正的风电功率优化预测[J]. 电力自动化设备, 2019, 39(3): 182-188.
XIAO Y, LI C H, LIU R P, et al.Optimal prediction of wind power based on the correction of wind speed local climbing error[J]. Electric power automation equipment, 2019, 39(3): 182-188.
[8] 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802.
ZHU Q M, LI H Y, WANG Z Q, et al.Short-term wind power forecasting based on LSTM[J]. Power system technology, 2017, 41(12): 3797-3802.
[9] 杨茂, 刘慧宇, 孙勇, 等. 基于原子稀疏分解和支持向量机的风电功率实时预测研究[J]. 东北电力大学学报, 2020, 40(3): 1-7.
YANG Mao, LIU Huiyu, SUN Yong, et al.Research on real-time prediction of wind power based on atomic sparse decomposition and support vector machine[J]. Journal of Northeast Electric Power University, 2020, 40(3): 1-7.
[10] 张学清, 梁军, 张熙, 等. 基于样本熵和极端学习机的超短期风电功率组合预测模型[J]. 中国电机工程学报, 2013, 33(25): 33-40, 8.
ZHANG X Q, LIANG J, ZHANG X, et al.Combined prediction model of ultra-short-term wind power based on sample entropy and extreme learning machine[J]. Proceedings of the CSEE, 2013, 33(25): 33-40, 8.
[11] 彭晨宇, 陈宁, 高丙团. 结合多重聚类和分层聚类的超短期风电功率预测方法[J]. 电力系统自动化, 2020, 44(2): 173-181.
PENG C Y, CHEN N, GAO B T.Ultra-short-term wind power forecasting method combining multi-clustering and hierarchical clustering[J]. Automation of electric power systems, 2020, 44(2): 173-181.
[12] 徐龙博, 王伟, 张滔, 等. 基于神经网络平均影响值的超短期风电功率预测[J]. 电力系统自动化, 2017, 41(21): 40-45.
XU L B, WANG W, ZHANG T, et al.Ultra-short-term wind power prediction based on the average influence value of neural network[J]. Power system automation, 2017, 41(21): 40-45.
[13] TIAN Y X, LI P.Predicting short-term traffic flow by long short-term memory recurrent neural network[C]//IEEE International Conference on Smart City, Chengdu, China, 2015.
[14] HUANG G B, ZHU Q Y, SIEW C K.Extreme learning machine: theory and applications[J]. Neuro computing, 2006, 70(1/2/3): 489-501.
[15] LIANG N Y, HUANG GB, SARATCHANDRANP, et al. A fast and accurate online sequential learning algorithm for feed forward networks[J]. IEEE transactions on neural networks, 2006, 17(6): 1411-1423.
[16] 刘纯, 范高锋, 王伟胜, 等. 风电场输出功率的组合预测模型[J]. 电网技术, 2009, 33(13): 74-79.
LIU C, FAN G F, WANG W S, et al.Combined prediction model of wind farm output power[J]. Power system technology, 2009, 33(13): 74-79.
[17] MENG X, GAO X Z, LU L, et al.A new bio-inspired optimisation algorithm: bird swarm algorithm[J]. Journal of experimental & theoretical artificial intelligence, 2016, 28(4): 673-687.
[18] 赵佩, 代业明. 基于实时电价和加权灰色关联投影的SVM电力负荷预测[J]. 电网技术, 2020, 44(4): 1325-1332.
ZHAO P, DAI Y M.SVM power load forecasting based on real-time electricity price and weighted grey correlation projection[J]. Power system technology, 2020, 44(4): 1325-1332.
[19] 杨志超, 张成龙, 葛乐, 等. 基于熵权法的绝缘子污闪状态模糊综合评价[J]. 电力自动化设备, 2014, 34(4):90-94.
YANG Z C, ZHANG C l, GE L, et all. Fuzzy comprehensive evaluation of insulator flashover state based on entropy weight method[J]. Electric power automation equipment, 2014, 34(4): 90-94.
[20] Q/GDW 10588—2015, 风电功率预测功能规范[S].
Q/GDW 10588—2015, Wind power prediction function specification[S].