区域风电场群集中式功率预测系统设计与应用

Jie YAN; Yongrui ZHANG; Hao ZHANG

doi:10.16513/j.2096-2185.DE.2207104

PDF(8106 KB)

分布式能源 ›› 2022, Vol. 7 ›› Issue (1) : 28-36. DOI: 10.16513/j.2096-2185.DE.2207104

学术研究

区域风电场群集中式功率预测系统设计与应用

Jie YAN ¹^,² ,
Yongrui ZHANG ¹^,² ,
Hao ZHANG ¹^,²

作者信息 +

Design and Application of Centralized Power Forecasting System for Regional Wind Farm Cluster

Jie YAN ¹^,² ,
Yongrui ZHANG ¹^,² ,
Hao ZHANG ¹^,²

Author information +

文章历史 +

本文亮点

风电功率预测系统大多遵循一个风电场配置一套预测系统的“一场一测”开发模式，此种模式下区域内相邻风电场的数据不能汇聚，预测模型无法充分考虑场站间的时空依赖关系来提升预测精度，大量独立的预测系统也无法得到统一、高效的维护。为此，提出了一种区域风电场群集中式功率预测系统。首先，该系统引入了多源数值天气预报数据作为模型输入；接着，在预测系统中进行了风机级和站级的数据清洗；最后，在预测系统中设计了风电场群时空联合预测模型。该模型可以捕捉区域内各风电场间的时空依赖性，能够同时为区域内所有风电场提供短期、超短期预测结果。所设计的系统应用于由10个风电场构成的风电场群的区域风电集控中心，在线运行结果表明，该预测系统符合区域电网评估要求，10个风电场在评估中排名靠前，运行期内预测考核扭亏为盈。

HeighLight

Wind power forecasting system mostly follows the development mode of "one wind farm, one forecasting system" , in which one wind farm is equipped with one set of forecasting system. In this mode, the data of adjacent wind farms within the region cannot be aggregated, the prediction model cannot fully consider the spatio-temporal dependence between the stations to improve the prediction accuracy, and a large number of independent prediction systems cannot be maintained uniformly and efficiently. Therefore, a regional wind farm cluster Chinese power prediction system is proposed. Firstly, multi-source numerical weather forecast data are introduced as the input of the model. Then, the data of fan level and station level are cleaned in the prediction system. Finally, the spatio-temporal combined prediction model of wind farm group is designed in the prediction system. The model can capture the temporal and spatial dependence of wind farms in the region and provide short-term and ultra-short-term prediction results for all wind farms in the region simultaneously. The designed system is referenced in the regional wind power centralized control center of the wind farm group composed of 10 wind farms. The online operation results show that the prediction system meets the requirements of regional power grid evaluation. The 10 wind farms rank top in the evaluation, and the prediction assessment turns from loss to profit during the operation period.

导出引用

Jie YAN, Yongrui ZHANG, Hao ZHANG. 区域风电场群集中式功率预测系统设计与应用[J]. 分布式能源. 2022, 7(1): 28-36 https://doi.org/10.16513/j.2096-2185.DE.2207104

Jie YAN, Yongrui ZHANG, Hao ZHANG. Design and Application of Centralized Power Forecasting System for Regional Wind Farm Cluster[J]. Distributed Energy Resources. 2022, 7(1): 28-36 https://doi.org/10.16513/j.2096-2185.DE.2207104

中图分类号： TK81

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]	ZHANG Y, WANG J, WANG X. Review on probabilistic forecasting of wind power generation[J]. Renewable and Sustainable Energy Reviews, 2014(32), 255-270. 本文引用 [2]

[2]	张晋华，冯源，黄远为，等. 基于EMD-RVM的风电场机组分组功率预测[J]. 分布式能源，2021, 6(2): 10. ZHANG Jinhua, QIAO Yuan, HUANG Yuanwei, et al. Power prediction for groups of wind farms units based on EMD-RVM[J]. Distributed Energy, 2021, 6(2): 10. 本文引用 [1]

[3]	刘栋，魏霞，王维庆，等. 基于SSA-ELM的短期风电功率预测[J]. 智慧电力，2021, 49(6): 53-59. LIU Dong, WEI Xia, WANG Weiqing, et al. Short-term wind power prediction based on SSA-ELM[J]. Smart Power, 2021, 49(6): 53-59. 本文引用 [1]

[4]	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. PENG Xiaosheng, XIONG Lei, WEN Jinyu, et al. A summary of the state of the art for short-term and ultra-short-term wind power prediction of regions[J]. Proceedings of the CSEE, 2016, 36(23): 6315-6326. 本文引用 [1]

[5]	叶林，赵永宁. 基于空间相关性的风电功率预测研究综述[J]. 电力系统自动化，2014, 38(14): 126-135. YE Lin, ZHAO Yongning. A review on wind power prediction based on spatial correlation approach[J]. Automation of Electric Power Systems, 2014, 38(14): 126-135. 本文引用 [1]

[6]	黄树帮，陈耀，金宇清. 碳中和背景下多通道特征组合超短期风电功率预测[J]. 发电技术，2021, 42(1): 60-68. HUANG Shubang, CHEN Yao, JIN Yuqing. A multi-channel feature combination model for ultra-short-term wind power prediction under carbon neutral background[J]. Power Generation Technology, 2021, 42(1): 60-68. 本文引用 [1]

[7]	GNEITING T, LARSON K, WESTRICK K, et al. Calibrated probabilistic forecasting at the stateline wind energy center: the regime-switching space: time method[J]. Journal of the American Statistical Association, 2006, 101(475): 968-979. 本文引用 [1]

[8]	HERING A S, GENTON M G. Powering up with space-time wind forecasting[J]. Journal of the American Statistical Association, 2010, 105(489): 92-104. 本文引用 [1]

[9]	XIE L, GU Y, ZHU X, et al. Short-term spatio-temporal wind power forecast in robust look-ahead power system dispatch[J]. IEEE Transactions on Smart Grid, 2014, 5(1): 511-520. 本文引用 [1]

[10]	TASTU J, PINSON P, KOTWA E, et al. Spatio-temporal analysis and modeling of short-term wind power forecast errors[J]. Wind Energy, 2011, 14(1). 本文引用 [1]

[11]	DOWELL J, WEISS S, HILL D, et al. Short-term spatio-temporal prediction of wind speed and direction[J]. Wind Energy, 2015, 17(12): 1945-1955. 本文引用 [1]

[12]	WANG Z, WANG W, LIU C, et al. Probabilistic forecast for multiple wind farms based on regular vine copulas[J]. IEEE Transactions on Power Systems, 2018, 33(1): 578-589. 本文引用 [1]

[13]	MANGALOVA E, SHESTERNEVA O. K-nearest neighbors for GEFCom2014 probabilistic wind power forecasting[J]. International Journal of Forecasting, 2016, 32(1): 1067-1073. 本文引用 [1]

[14]	LANDRY M, EDINGER T. P, PATSCHKE D, et al. Probabilistic gradient boosting machines for GEFCom2014 wind forecasting[J]. International Journal of Forecasting, 2016, 32(3): 1061-1066. 本文引用 [1]

[15]	DOWELL J, PINSON P. Very-short-term probabilistic wind power forecasts by sparse vector autoregression[J]. IEEE Transactions on Smart Grid, 2015, 7(2): 1-1. 本文引用 [1]

[16]	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. 本文引用 [1]

[17]	ZHAO Y, YE L, PINSON P, et al. Correlation-constrained and sparsity-controlled vector autoregressive model for spatio-temporal wind power forecasting[J]. IEEE Transactions on Power Systems, 2018, 33(5): 5029-5040. 本文引用 [1]

[18]	PINSON P. Introducing distributed learning approaches in wind power forecasting[C]//2016 International Conference on Probabilistic Methods Applied to Power Systems, Beijing, China, 2016, 1-6. 本文引用 [1]

[19]	ZHANG Y, WANG J. A distributed approach for wind power probabilistic forecasting considering spatio-temporal correlation without direct access to off-site information[J]. IEEE Transactions on Power Systems, 2018, 33(5): 1-1. 本文引用 [1]

[20]	刘永前，林爱美，阎洁，等. 基于深度学习的风光场群功率预测方法研究[J]. 分布式能源，2021, 6(2): 8. LIU Yongqian, LIN Aimei, YAN Jie, et al. Research on power forecasting for wind farms and photovoltaic stations based on deep learning[J]. Distributed Energy, 2021, 6(2): 8. 本文引用 [1]

[21]	THU T, WU W, GUO Q, et al. Very short-term spatial and temporal wind power forecasting: A deep learning approach[J]. CSEE Journal of Power and Energy Systems, 2019, 6(2): 1-10. 本文引用 [1]

[22]	GHADERI A, SANANDAJI B M, GHADERI F. Deep forecast: Deep learning-based spatio-temporal forecasting[C]//ICML 2017. 本文引用 [1]

[23]	ZHU Q, CHEN J, SHI D, et al. Learning temporal and spatial correlations jointly: a unified framework for wind speed prediction[J]. IEEE Transactions on Sustainable Energy, 2020, 11(1): 509-523 本文引用 [1]

[24]	YAN J, ZHANG H, LIU Y, et al. Forecasting the high penetration of wind power on multiple scales using multi-to-multi mapping[J]. IEEE Transactions on Power Systems, 2018, 33(3): 3276-3284. 本文引用 [2]

[25]	ZHANG H, LIY Y, YAN J, et al. Improved deep mixture density network for regional wind power probabilistic forecasting[J]. IEEE Transactions on Power Systems, 2020, 35(4): 2549-2560. 本文引用 [2]

[26]	MAHDI K, WANG J. Spatio-temporal graph deep neural network for short-term wind speed forecasting[J]. IEEE Transactions on Sustainable Energy, 2018, 10(2): 1-1. 本文引用 [2]

[27]	YAN J, ZHANG H, LIU Y, et al. Uncertainty estimation for wind energy conversion by probabilistic wind turbine power curve modelling[J]. Applied Energy, 2019, 239(1): 1356-1370. 本文引用 [1]

[28]	LONG H, SANG L, WU Z, et al. Image-based abnormal data detection and cleaning algorithm via wind power curve[J]. IEEE Transactions on Sustainable Energy, 2020, 11(2): 938-946. 本文引用 [1]