基于Attention-GRU风速修正和Stacking的短期风电功率预测

doi:10.19912/j.0254-0096.tynxb.2021-0712

太阳能学报 ›› 2022, Vol. 43 ›› Issue (12): 273-281.DOI: 10.19912/j.0254-0096.tynxb.2021-0712

基于Attention-GRU风速修正和Stacking的短期风电功率预测

杨国清^1,2, 刘世林¹, 王德意^1,2, 王文坤¹, 刘菁^1,2

1.西安理工大学电气工程学院,西安 710054;
2.西安市智慧能源重点实验室（西安理工大学）,西安 710054

收稿日期:2021-06-23 出版日期:2022-12-28 发布日期:2023-06-28
通讯作者: 杨国清（1979—）,男,博士、副教授,主要从事电力系统新能源消纳、高电压新技术等方面的研究。yanggq@xaut.edu.cn
基金资助:
国家自然科学基金（51507134）; 陕西省重点研发计划（2018ZDXM-GY-169）; 西安市科技创新平台建设项目（201805057ZD8CG41）

SHORT-TERM WIND POWER FORECASTING BASED ON ATTENTION-GRU WIND SPEED CORRECTION AND STACKING

Yang Guoqing^1,2, Liu Shilin¹, Wang Deyi^1,2, Wang Wenkun¹, Liu Jing^1,2

1. School of Electrical Engineering, Xi’an University of Technology, Xi’an 710054, China;
2. Xi’an Key Laboratory of Smart Energy,Xi’an University of Technology, Xi’an 710054, China

Received:2021-06-23 Online:2022-12-28 Published:2023-06-28

摘要/Abstract

摘要： 针对使用数值天气预报（NWP）数据进行风电功率预测时,NWP风速与实际风速存在偏差导致预测精度欠佳,提出一种基于注意力机制（Attenion）门控逻辑单元（GRU）数值天气预报风速修正和Stacking多算法融合的短期风电功率预测模型。首先,分析NWP预报风速和实际风速的皮尔逊相关系数,建立Attention-GRU风速修正模型,提高预报风速精度。其次,考虑风向、温度、湿度、气压、空气密度等气象因素,基于Stacking框架,提出融合XGBoost、LSTM、SVR、LASSO的多算法风电功率预测模型,同时采用网格搜索与交叉验证优化模型参数。最后,选取西北和东北两个典型风电场数据进行验证,算例结果表明,所提出模型能改善NWP风速精度并提升风电功率预测效果。

关键词: 风电, 预测, 天气预报, 深度学习, 集成学习

Abstract: In view of the low accuracy of wind power forecasting due to the deviation of NWP wind speed and actual wind speed when using numerical weather prediction（NWP） data, this paper proposes a short-term wind power forecasting model based on Attention-GRU NWP wind speed correction and multi-algorithm fusion under Stacking framework. Firstly, the Pearson correlation coefficient between NWP prediction wind speed and actual wind speed is analyzed, and a wind speed correction model based on Attention-GRU is established to improve the precision of prediction wind speed. Secondly, considering the meteorological factors such as wind direction, temperature, humidity, air pressure and air density, a multi-algorithm wind power forecasting model based on Stacking framework is proposed, which integrates XGBoost, LSTM, SVR and LASSO. Grid search and cross-validation are used to optimize the model parameters. Finally, two typical wind farms in Northwest and Northeast China are selected to verify the model. The results show that the proposed model can improve the precision of NWP wind speed forecast and effectively improve the forecasting effect of wind power.

Key words: wind power, forecasting, weather forecasting, deep learning, ensemble learning

中图分类号:

TM614

杨国清, 刘世林, 王德意, 王文坤, 刘菁. 基于Attention-GRU风速修正和Stacking的短期风电功率预测[J]. 太阳能学报, 2022, 43(12): 273-281.

Yang Guoqing, Liu Shilin, Wang Deyi, Wang Wenkun, Liu Jing. SHORT-TERM WIND POWER FORECASTING BASED ON ATTENTION-GRU WIND SPEED CORRECTION AND STACKING[J]. Acta Energiae Solaris Sinica, 2022, 43(12): 273-281.

参考文献

[1] 林伯强. “十三五”时期中国电力发展成就及“十四五”展望[J]. 中国电业, 2020(12): 22-23.
LIN B Q.China’s electric power development achievements during the “13th Five-Year Plan”period and prospects for the “14th Five-Year Plan”[J]. China electric power, 2020(12): 22-23.
[2] 杨秀媛, 肖洋, 陈树勇. 风电场风速和发电功率预测研究[J]. 中国电机工程学报, 2005(11): 3-7.
YANG X Y, XIAO Y, CHEN S Y.Wind speed and generated power forecasting in wind farm[J]. Proceedings of the CSEE, 2005(11): 3-7.
[3] 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.Comments on short-term and ultra-short-term wind power forecasting[J]. Automation of electric power systems, 2015, 39(6): 141-151.
[4] 刘帅, 朱永利, 张科, 等. 基于误差修正ARMA-GARCH模型的短期风电功率预测[J]. 太阳能学报, 2020, 41(10): 268-275.
LIU S, ZHU Y L, ZHANG K, et al.Short-term wind power forecasting based on error correction ARMA-GARCH model[J]. Acta energiae solaris sinica, 2020, 41(10): 268-275.
[5] YANG L, HE M, ZHANG J, et al.Support-vector-machine-enhanced Markov model for short-term wind power forecast[J]. IEEE transactions on sustainable energy, 2017, 6(3): 791-799.
[6] 黄慧, 贾嵘, 董开松. 基于时空相关性的NAR动态神经网络风功率超短期组合预测[J]. 太阳能学报, 2020, 41(10): 311-316.
HUANG H, JIA R, DONG K S.Ultra short-termcombined forecasting of wind power with NAR neural network based on spatio-temporal correlation[J]. Acta energiae solaris sinica, 2020, 41(10): 311-316.
[7] HAN L, ZHANG R, WANG X, et al.Multi-step wind power forecast based on VMD-LSTM[J]. IET renewable power generation, 2019, 13(10): 1690-1700.
[8] 汪欣, 蔡旭, 李征. 结合交叉局部异常因子和注意力机制的超短期风电功率预测方法[J]. 电力系统保护与控制, 2020, 48(23):92-99.
WANG X, CAI X, LI Z.Ultra-short-term wind power forecasting method based on a cross LOF preprocessing algorithm and an attention mechanism[J]. Power system protection and control, 2020, 48(23): 92-99.
[9] DU P W.Ensemble machine learning-based wind forecasting to combine NWP output with data from weather station[J]. IEEE transactions on sustainable energy, 2019, 10(4): 2133-2141.
[10] ANDRADE J R., BESSA R J.Improving renewable energy forecasting with a grid of numerical weather predictions[J]. IEEE transactions on sustainable energy, 2017, 8(4): 1571-1580.
[11] 杨茂, 白玉莹. 基于多位置NWP和门控循环单元的风电功率超短期预测[J]. 电力系统自动化, 2021, 45(1):177-183.
YANG M, BAI Y Y.Ultra-short-term prediction of wind power based on multi-location numerical weather prediction and gated recurrent unit[J]. Automation of electric power systems, 2021, 45(1): 177-183.
[12] 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.
[13] 李永刚, 王月, 刘丰瑞, 等. 基于Stacking融合的短期风速预测组合模型[J]. 电网技术, 2020, 44(8): 2875-2882.
LI Y G, WANG Y, LIU F R, et al.Combination model of short-term wind speed prediction based on stacking fusion[J]. Power system technology, 2020, 44(8): 2875-2882.
[14] 史佳琪, 张建华. 基于多模型融合Stacking集成学习方式的负荷预测方法[J]. 中国电机工程学报, 2019, 39(14): 4032-4042.
SHI J Q, ZHANG J H.Load forecasting based on multi-model by stacking ensemble learning[J]. Proceedings of the CSEE, 2019, 39(14): 4032-4042.
[15] 杨国清, 张凯, 王德意, 等. 基于包络线聚类的多模融合超短期光伏功率预测算法[J]. 电力自动化设备, 2021, 41(2): 39-46.
YANG G Q, ZHANG K, WANG D Y, et al.Multi-mode fusion ultra-short-term photovoltaic power prediction algorithm based on envelope clustering[J]. Electric power automation equipment, 2021, 41(2): 39-46.
[16] 乔颖, 鲁宗相, 闵勇. 提高风电功率预测精度的方法[J]. 电网技术, 2017, 41(10): 3261-3268.
QIAO Y, LU Z X, MIN Y.Methods of improving wind power forecasting accuracy[J]. Power system technology, 2017, 41(10): 3261-3268.
[17] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[18] CHUNG J Y, GULCEHRE C, CHO K H, et al.Empirical evaluation of gated recurrent neural networks on sequence modeling: Eprint Arxiv, 10.48550/arXiv. 1412.3555[P]. 2014.
[19] LUONG M T, PHAM H, MANNING C D.Effective approaches to attention-based neural machine translation[J/OL]. Computer science, 2015.
[20] XIONG L, ZHOU W, WANG W, et al.Attention-based relation extraction with bidirectional gated recurrent unit and highway network in the analysis of geological data[J]. IEEE access, 2018, 6: 5705-5715.
[21] CAVALCANTE L, BESSA R J, REIS M, et al.LASSO vector autoregression structures for very short-term wind power forecasting[J]. Wind energy, 2017, 20(4): 657-675.

基于Attention-GRU风速修正和Stacking的短期风电功率预测

SHORT-TERM WIND POWER FORECASTING BASED ON ATTENTION-GRU WIND SPEED CORRECTION AND STACKING

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	马建民, 单士睿. 基于虚拟惯性的双馈异步风力发电机控制方法及其稳定性分析[J]. 太阳能学报, 2022, 43(9): 202-210.
[2]	刘宪庆, 赵明阶, 乐丛欢, 余葵, 罗盛. 静水及波浪中四筒型基础的动力及运动特性研究[J]. 太阳能学报, 2022, 43(9): 211-217.
[3]	石嫄嫄, 和庆冬, 吴衍剑, 杜君峰, 张敏. 基于多失效模式的海上浮式风电机组结构可靠性研究[J]. 太阳能学报, 2022, 43(9): 236-241.
[4]	姜军倪, 董霄峰, 王海军, 练继建. 海上风电结构横风向气动力阻尼特性研究[J]. 太阳能学报, 2022, 43(9): 267-272.
[5]	熊根, 王滨, 陆南辛, 夏露, 祝周杰. 基于改进Prony变换的时频分析方法及其在海上风电结构中的应用研究[J]. 太阳能学报, 2022, 43(9): 280-286.
[6]	花志锋, 赵荣珍. 风电齿轮箱行星轮系的齿面摩擦与齿根裂纹耦合效应计算方法[J]. 太阳能学报, 2022, 43(9): 287-293.
[7]	曹洁, 张玉林, 王进花, 余萍. 基于VMD和SVPSO-BP的滚动轴承故障诊断[J]. 太阳能学报, 2022, 43(9): 294-301.
[8]	王景华, 张磊安, 李成良, 黄雪梅, 刘卫生, 李建伟. 基于改进的显式算法对叶片模具翻转架的失效调查[J]. 太阳能学报, 2022, 43(9): 302-307.
[9]	张家安, 刘东, 刘辉, 宋鹏, 刘京波, 吴宇辉. 基于风速波动特征提取的超短期风速预测[J]. 太阳能学报, 2022, 43(9): 308-313.
[10]	肖运启, 李浩志, 卢泽众, 马静静, 付楠. 大型风电场多Agent系统建模仿真及降损控制[J]. 太阳能学报, 2022, 43(9): 314-320.
[11]	张振海, 王维庆, 王海云, 曹源. 基于改进小波包的风电机组齿轮箱复合故障特征提取研究[J]. 太阳能学报, 2022, 43(9): 331-336.
[12]	德雪红, 杨洋, 金敏, 李南丁, 郭文斌, 李震. 生物质成型机成型模孔内表面摩擦力分形预测[J]. 太阳能学报, 2022, 43(9): 369-375.
[13]	刘华兵, 张庆贺, 刘艳娇, 彭爱武. 基于磁流体发电机的波浪能最大功率追踪策略研究[J]. 太阳能学报, 2022, 43(9): 402-409.
[14]	欧阳静, 杨吕, 尹康, 赵宇航, 潘国兵. 基于ALIF-LSTM多任务学习的综合能源系统短期负荷预测[J]. 太阳能学报, 2022, 43(9): 499-507.
[15]	袁建华, 谢斌斌, 何宝林, 赵子玮, 刘宇, 刘邦. 基于DTW-VMD-PSO-BP的光伏发电功率短期预测方法[J]. 太阳能学报, 2022, 43(8): 58-66.