李炳胜,庞传军,程大闯
LI Bingsheng,PANG Chuanjun,CHENG Dachuang

• 1:南瑞集团有限公司(国网电力科学研究院有限公司)
• 2:北京科东电力控制系统有限责任公司

摘要(Abstract)：

为实现风电功率概率预测，分析预测结果的影响因素，提出一种基于NGBoost（自然梯度提升）算法并考虑可解释性的风电功率概率预测方法。首先，在分析风电功率特性的基础上给出风电功率概率预测模型的定义，利用NGBoost算法训练预测模型，实现考虑风电功率异方差特性的概率预测；然后，利用合作博弈论中的Shapley值对预测模型进行解释，分析气象因素对预测结果的影响；最后，采用实际风电场数据验证模型的预测性能，并与其他方法进行比较。结果表明，所提方法取得了较好的预测效果，并且能够解释预测结果，分析气象因素对预测结果的影响是一种兼具实用性和有效性的风电功率概率预测方法。
To realize the probabilistic prediction of wind power and analyze the influencing factors of the prediction results, this paper proposes a probabilistic prediction method of wind power based on natural gradient boosting(NGBoost) and takes account of interpretable wind power probabilistic forecast method. Firstly, the definition of a probabilistic wind power prediction model is given based on the analysis of wind power characteristics. The NGBoost algorithm is used to train the prediction model to achieve probabilistic prediction considering the heteroskedasticity characteristics of wind power. Secondly, the Shapley value in cooperative game theory is used to interpret the prediction model and analyze the influence of meteorological factors on the prediction results. Finally, the prediction performance of the model is verified using actual wind farm data and compared with other methods. The results show that the proposed method achieves good prediction effect and can explain the prediction results and analyze the influence of meteorological factors on the prediction results. The method is practical and effective.

关键词(KeyWords)： 风电功率概率预测;风电功率不确定性;梯度提升算法;Shapley值
wind power probabilistic prediction;wind power uncertainty;NGBoost;Shapley value

Abstract:

Keywords:

基金项目(Foundation): 国家电网有限公司科技项目（5108-202218280A-2-277-XG）

作者(Author): 李炳胜,庞传军,程大闯
LI Bingsheng,PANG Chuanjun,CHENG Dachuang

DOI: 10.19585/j.zjdl.202303004

参考文献(References)：

• [1]辛保安.为实现“碳达峰、碳中和”目标贡献智慧和力量[N].人民日报，2021-02-23(10).
• [2]国家电网公司.国家电网公司“碳达峰、碳中和”行动方案[EB/OL].北京：国家电网公司，（2021-03-01）[2021-03-03].http：//www.sgcc.com.cn/html/sgcc_main/col2017021449/2021-03/01/20210301152244682318653_1.shtml.
• [3]孙堃，赵萌萌，沈美娜，等.基于CEEMD和模糊熵的随机森林风力发电功率预测[J].智慧电力，2019,47(10):36-43.SUN Kun,ZHAO Mengmeng,SHEN Meina,et al.Wind power forecasting with random forest based on CEEMD and fuzzy entropy[J].Smart Power,2019,47(10):36-43.
• [4]韩自奋，景乾明，张彦凯，等.风电预测方法与新趋势综述[J].电力系统保护与控制，2019,47(24):178-187.HAN Zifen,JING Qianming,ZHANG Yankai,et al.Review of wind power forecasting methods and new trends[J].Power System Protection and Control,2019,47(24):178-187.
• [5]张峰，张鹏，梁军.考虑风电功率不确定性的风电场出力计划上报策略[J].电力自动化设备，2019,39(11):34-40.ZHANG Feng,ZHANG Peng,LIANG Jun. Wind farm generation schedule strategy considering wind power uncertainty[J]. Electric Power Automation Equipment,2019,39(11):34-40.
• [6]万灿，宋永华.新能源电力系统概率预测理论与方法及其应用[J].电力系统自动化，2021,45(1):2-16.WAN Can,SONG Yonghua.Theories,methodologies and applications of probabilistic forecasting for power systems with renewable energy sources[J].Automation of Electric Power Systems,2021,45(1):2-16.
• [7]吴问足，乔颖，鲁宗相，等.风电功率概率预测方法及展望[J].电力系统自动化，2017,41(18):167-175.WU Wenzu,QIAO Ying,LU Zongxiang,et al. Methods and prospects for probabilistic forecasting of wind power[J]. Automation of Electric Power Systems,2017,41(18):167-175.
• [8]叶瑞丽，刘建楠，苗峰显，等.风电场风电功率预测误差分析及置信区间估计研究[J].陕西电力，2017,45(2):21-25.YE Ruili,LIU Jiannan,MIAO Fengxian,et al.Analysis of wind power prediction error and its confidence interval estimation in wind farms[J].Shaanxi Electric Power,2017,45(2):21-25.
• [9]韩丽，乔妍，景惠甜.基于误差分类的风电功率区间评估[J].电力系统自动化，2021,45(1):97-104.HAN Li,QIAO Yan,JING Huitian.Interval estimation of wind power based on error classification[J].Automation of Electric Power Systems,2021,45(1):97-104.
• [10]杨锡运，张艳峰，叶天泽，等.基于朴素贝叶斯的风电功率组合概率区间预测[J].高电压技术，2020,46(3):1099-1108.YANG Xiyun,ZHANG Yanfeng,YE Tianze,et al.Prediction of combination probability interval of wind power based on naive Bayes[J].High Voltage Engineering,2020,46(3):1099-1108.
• [11]乔颖，鲁宗相，吴问足.考虑误差时序-条件性质的短期风电功率概率预测[J].电网技术，2020,44(7):2529-2537.QIAO Ying,LU Zongxiang,WU Wenzu.Day-ahead wind power probabilistic forecast considering conditional dependency and temporal correlation[J]. Power System Technology,2020,44(7):2529-2537.
• [12]杨茂，董昊.基于数值天气预报风速和蒙特卡洛法的短期风电功率区间预测[J].电力系统自动化，2021,45(5):79-85.YANG Mao,DONG Hao.Short-term wind power interval prediction based on wind speed of numerical weather prediction and Monte Carlo method[J].Automation of Electric Power Systems,2021,45(5):79-85.
• [13]王钊，王勃，冯双磊，等.区域多风电场功率的分位数回归概率预测方法[J].电网技术，2020,44(4):1368-1375.WANG Zhao,WANG Bo,FENG Shuanglei,et al.Probabilistic forecasts based on quantile regression for regional wind farms[J].Power System Technology,2020,44(4):1368-1375.
• [14]甘迪，柯德平，孙元章，等.基于集合经验模式分解和遗传-高斯过程回归的短期风速概率预测[J].电工技术学报，2015,30(11):138-147.GAN Di,KE Deping,SUN Yuanzhang,et al.Short-term wind speed probabilistic forecasting based on EEMD and coupling GA-GPR[J].Transactions of China Electrotechnical Society,2015,30(11):138-147.
• [15]江长明，杨健，柳玉，等.基于数据驱动的风电功率预测误差解耦评价方法[J].电力系统自动化，2021,45(1):105-113.JIANG Changming,YANG Jian,LIU Yu,et al. Datadriven decoupling evaluation method of wind power prediction error[J]. Automation of Electric Power Systems,2021,45(1):105-113.
• [16]杨茂，代博祉.基于比恩法的风电场风速-功率曲线建模误差分析[J].电力自动化设备，2020,40(12):81-89.YANG Mao,DAI Bozhi.Modeling error analysis of wind speed-wind power curve for wind farm based on Bins method[J].Electric Power Automation Equipment,2020,40(12):81-89.
• [17]杨建，张利，王明强，等.计及出力水平影响与自相关性的风电预测误差模拟方法[J].电力自动化设备，2017,37(9):96-102.YANG Jian,ZHANG Li,WANG Mingqiang,et al.Windpower forecasting error simulation considering output level and self-correlation[J].Electric Power Automation Equipment,2017,37(9):96-102.
• [18]王伟胜，王铮，董存，等.中国短期风电功率预测技术现状与误差分析[J].电力系统自动化，2021,45(1):17-27.WANG Weisheng,WANG Zheng,DONG Cun,et al.Status and error analysis of short-term forecasting technology of wind power in China[J].Automation of Electric Power Systems,2021,45(1):17-27.
• [19] DUAN T,AVATI A,DING D Y,et al.NGBoost:natural gradient boosting for probabilistic prediction[C]//Proceedings of the 37th International Conference on Machine Learning.New York:ACM,2020:2690-2700.
• [20]杨楠，黄禹，叶迪，等.基于NACEMD和改进非参数核密度估计的风功率波动性概率分布研究[J].电网技术，2019,43(3):910-917.YANG Nan,HUANG Yu,YE Di,et al.Study on probability distribution of wind power fluctuation based on NACEMD and improved nonparametric kernel density estimation[J]. Power System Technology,2019,43(3):910-917.
• [21]李力行，苗世洪，涂青宇，等.考虑异方差效应的风电不确定性建模及其在调度中的应用[J].电力系统自动化，2020,44(8):36-47.LI Lixing,MIAO Shihong,TU Qingyu,et al.Modelling of wind power uncertainty considering heteroskedasticity effect and its application in power system dispatching[J].Automation of Electric Power Systems,2020,44(8):36-47.
• [22]庞传军，余建明，张波，等.基于梯度提升树计及非线性的电力负荷影响因素分析[J].电力系统保护与控制，2020,48(24):71-78.PANG Chuanjun,YU Jianming,ZHANG Bo,et al.Nonlinear correlation analysis of influence factors of a power load based on a gradient boosting decision tree[J].Power System Protection and Control,2020,48(24):71-78.
• [23] DAWID A P. The geometry of proper scoring rules[J].Annals of the Institute of Statistical Mathematics,2007,59(1):77-93.
• [24] AMARI S I.Natural gradient works efficiently in learning[J].Neural Computation,1998,10(2):251-276.
• [25] MARTENS J. New insights and perspectives on the natural gradient method[EB/OL].[2022-03-16]. https：//arxiv.org/abs/1412.1193.
• [26] ALEXANDER L.A tutorial on fisher information[J].Journal of Mathematical Psychology,2017,80:40-55.
• [27] SHAPLEY L S.A value for n-person games[J].Contributions to the Theory of Games, 1953, 2(28):307-317.
• [28]陈星莺，郁清云，谢俊，等.基于合作博弈论的电能替代效益分摊方法[J].电力自动化设备，2019,39(3):30-35.CHEN Xingying,YU Qingyun,XIE Jun,et al.Benefit allocation method for electric energy substitution based on cooperative game theory[J]. Electric Power Automation Equipment,2019,39(3):30-35.
• [29] LUNDBERG S,LEE S.A unified approach to interpreting model predictions[C]//NIPS′17:Proceedings of the31st International Conference on Neural Information Processing Systems.Chicago,America:NIPS,2017.
• [30] LUNDBERG S M,ERION G,CHEN H,et al.From local explanations to global understanding with explainable AI for trees[J].Nature Machine Intelligence,2020,2(1):56-67.
• [31] CHRISTOPH M. Interpretable machine learning[EB/OL].[2021-09-08]. https：//christophm. github. io/interpretable-ml-book.