XGBoost方法在风电功率预报中的应用

doi:10.3969/j.issn.1673-503X.2025.03.005

气象与环境学报 ›› 2025, Vol. 41 ›› Issue (3): 36-43.doi: 10.3969/j.issn.1673-503X.2025.03.005

• 论文 • 上一篇

XGBoost方法在风电功率预报中的应用

段云霞^1,2, 李忠娴³, 李得勤^1,4,5

1. 中国气象局东北冷涡研究重点开放实验室, 辽宁沈阳 110166;
2. 沈阳市气象局, 辽宁沈阳 110168;
3. 辽宁省气象局财务核算中心, 辽宁沈阳 110166;
4. 中国气象局沈阳大气环境研究所, 辽宁沈阳 110166;
5. 沈阳农业与生态气象研究院, 辽宁沈阳 110166

收稿日期:2024-06-12 修回日期:2025-02-06 发布日期:2025-09-29
通讯作者: 李得勤,男,正高级工程师,E-mail:Lewen05@hotmail.com。 E-mail:Lewen05@hotmail.com
作者简介:段云霞,女,1983年生,高级工程师,主要从事天气预报和灾害性天气机理研究工作,E-mail:yxduan@163.com。
基金资助:
国家自然科学基金(42275171)资助。

Application of the XGBoost method in wind power forecasting

Duan Yunxia^1,2, Li Zhongxian³, Li Deqin^1,4,5

1. Key Laboratory of Northeast Cold Vortex Research China Meteorological Administration, Shenyang 110166, China;
2. Shenyang Meteorological Service, Shenyang 110168, China;
3. Financial Accounting Center of Liaoning Meteorological Service, Shenyang 110166, China;
4. Institute of Atmospheric Environment, China Meteorological Administration, Shenyang 110166, China;
5. Shenyang Institute of Agricultural and Ecological Meteorology, Shenyang 110166, China

Received:2024-06-12 Revised:2025-02-06 Published:2025-09-29

摘要/Abstract

摘要： 使用2014年全球能源预测竞赛(GEFCom2014)风电功率观测和训练数据,开展基于XGBoost机器学习方法在风电功率预报中的应用研究。为考察不同变量数值分布对机器学习的可能影响,分别使用纬向风和经向风,以及风速和风向作为特征变量建立风电功率预报模型,并进行预报试验。结果表明:实际观测功率和数值预报风速的分布虽然整体符合风能功率曲线,但离散度过大。纬向风和经向风与风功率的相关性虽然不高,但作为XGBoost的训练特征变量,最终建立的模型具有较好的预报效果,与直接使用风速和风向建立的模型预报性能接近。模型预报结果呈现对风能峰值低估,以及低功率高估的情况,这可能与数值模式预报的风速存在误差有关。

关键词: 风电功率, 机器学习, XGBoost, 风能预报

Abstract: Using the wind power observation and training data from the 2014 Global Energy Forecasting Competition (GEFCom2014),a study on the application of the XGBoost machine learning method in wind power forecasting was conducted.To assess the potential influence of variable distribution on machine learning models,wind power forecasting models were developed using zonal wind and meridional wind,as well as wind speed and wind direction as feature variables.Forecast experiments show that although the distributions of actual observed wind power and numerically forecasted wind speed generally follow the wind power curve,the high degree of dispersion is a major factor contributing to the uncertainty in wind power forecasts.While the correlation between zonal/meridional winds and wind power is not high,models trained with these features using XGBoost still achieve good forecasting performance comparable to those built directly with wind speed and wind direction.The forecast results of the models tend to underestimate wind power peaks and overestimate low power values,which may be attributed to errors in numerically forecasted wind speed.

Key words: Wind power, Machine learning, XGBoost, Wind energy forecasting

中图分类号:

TK81

段云霞, 李忠娴, 李得勤. XGBoost方法在风电功率预报中的应用[J]. 气象与环境学报, 2025, 41(3): 36-43.

Duan Yunxia, Li Zhongxian, Li Deqin. Application of the XGBoost method in wind power forecasting[J]. Journal of Meteorology and Environment, 2025, 41(3): 36-43.

参考文献

[1] 杨振斌,薛桁,桑建国.复杂地形风能资源评估研究初探[J].太阳能学报,2004,25(6):744-749.
[2] 李泽椿,朱蓉,何晓凤,等.风能资源评估技术方法研究[J].气象学报,2007,65(5):708-717.
[3] Lewis J I.Wind energy in China:getting more from wind farms[J].Nature Energy,2016,1(6):16076.
[4] Zhang D H,Wang J Q,Lin Y G,et al.Present situation and future prospect of renewable energy in China[J].Renewable and Sustainable Energy Reviews,2017,76:865-871.
[5] Hua Y P,Oliphant M,Hu E J.Development of renewable energy in Australia and China:a comparison of policies and status[J].Renewable Energy,2016,85:1044-1051.
[6] Duan H B.Emissions and temperature benefits:the role of wind power in China[J].Environmental Research,2017,152:342-350.
[7] Zheng J Q,Du J,Wang B H,et al.A hybrid framework for forecasting power generation of multiple renewable energy sources[J].Renewable and Sustainable Energy Reviews,2023,172:113046.
[8] Atuahene S,Bao Y K,Ziggah Y Y,et al.Short-term electric power forecasting using dual-stage hierarchical wavelet-Particle swarm optimization-Adaptive neuro-fuzzy inference system PSO-ANFIS approach based on climate change[J].Energies,2018,11(10):2822.
[9] 李得勤,周晓珊,陈力强,等.基于数值模式的风速预报方法研究[J].太阳能学报,2012,33(10):1683-1689.
[10] 孙川永,陶树旺,罗勇,等.高分辨率中尺度数值模式在风电场风速预报中的应用[J].太阳能学报,2009,30(8):1097-1099.
[11] 柳艳香,陶树旺,张秀芝.风能预报方法研究进展[J].气候变化研究进展,2008,4(4):209-214.
[12] Cali U,Sharma V.Short-term wind power forecasting using long-short term memory based recurrent neural network model and variable selection[J].International Journal of Smart Grid and Clean Energy,2019,8(2):103-110.
[13] Wang H Z,Lei Z X,Zhang X,et al.A review of deep learning for renewable energy forecasting[J].Energy Conversion and Management,2019,198:111799.
[14] Bouabdallaoui D,Haidi T,Elmariami F,et al.Application of four machine-learning methods to predict short-horizon wind energy[J].Global Energy Interconnection,2023,6(6):726-737.
[15] Demolli H,Dokuz A S,Ecemis A,et al.Wind power forecasting based on daily wind speed data using machine learning algorithms[J].Energy Conversion and Management,2019,198:111823.
[16] Lahouar A,Slama J B H.Hour-ahead wind power forecast based on random forests[J].Renewable Energy,2017,109:529-541.
[17] Hong T,Pinson P,Fan S.Global energy forecasting competition 2012[J].International Journal of Forecasting,2014,30(2):357-363.
[18] Hong T,Pinson P,Fan S,et al.Probabilistic energy forecasting:global energy forecasting competition 2014 and beyond[J].International Journal of forecasting,2016,32(3):896-913.
[19] Chen T Q,Guestrin C.Xgboost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco:ACM,2016:785-794.
[20] Demolli H,Dokuz AS,Ecemis A,Gokcek M. Wind power forecasting based on daily wind speed data using machine learning algorithms[J].Energy Conversion and Management,2019,198,111823.

XGBoost方法在风电功率预报中的应用

Application of the XGBoost method in wind power forecasting

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

Metrics

本文评价

推荐阅读 0

[1]	张会, 陈军明, 王亚强, 马凤莲, 周煜, 卢宇坤, 刘通, 张良玉. 基于机器学习的CMA-MESO模式气温预报订正方法研究[J]. 气象与环境学报, 2025, 41(3): 18-28.
[2]	王俊秀, 张智, 李二杰, 姜学恭, 杨泽华, 王俊杰, 兰劲青. 基于多种机器学习算法构建的呼和浩特市臭氧气象条件评估指数对比分析[J]. 气象与环境学报, 2025, 41(2): 56-63.
[3]	张艳晴, 金晨曦, 闵晶晶, 韩超, 董颜, 齐晨. 基于机器学习的北京供暖季气温预报误差订正[J]. 气象与环境学报, 2025, 41(1): 58-65.
[4]	达瓦次仁,落追,洪一航,次仁卓嘎. 基于机器学习方法的气溶胶对西藏高原地区雨季降水的影响[J]. 气象与环境学报, 2024, 40(3): 138-144.
[5]	吴宇恒,白景昌. 基于遥感和机器学习的中国典型城市碳排放驱动因子及预测分析[J]. 气象与环境学报, 2024, 40(1): 105-112.
[6]	张煦庭, 刘慧, 刘瑞芳, 巨菲, 刘嘉慧敏, 高星星, 黄少妮, 王楠. 基于极端梯度提升算法的西安市逐小时PM_2.5浓度预报研究[J]. 气象与环境学报, 2023, 39(1): 44-54.
[7]	王涛, 王乙舒, 赵春雨, 王小桃, 秦美欧, 沈玉敏, 侯依玲, 赵建云. 基于机器学习方法的辽宁省初霜冻日期预测模型研究[J]. 气象与环境学报, 2022, 38(4): 47-56.
[8]	王远谋,李家启,陈施吉,唐家萍,夏佰成,韩世刚. 基于机器学习的重庆长江航道雾图像特征识别研究[J]. 气象与环境学报, 2021, 37(1): 106-112.