|
|
|
| Wind power prediction method based on XGBoost extended financial factor |
Yong-sheng WANG1,2( ),Shi-jie GUAN1,2,Li-min LIU1,2,*(),Jing GAO3,Zhi-wei XU1,2,Guang-wen LIU1,2 |
1. School of Data Science and Application, Inner Mongolia University of Technology, Hohhot 010080, China
2. Software Service Engineering Technology Research Center, Hohhot 010080, China
3. School of Computer and Information, Inner Mongolia Agricultural University, Hohhot 010018, China |
|
|
|
Abstract The main input characteristics of the existing wind power prediction models include meteorological data and power data. Aiming at the difficulties such as obtaining high-precision meteorological data, expressing the potential relationships between data, and slow convergence of the prediction models, the work proposed new ultra-short-term wind power prediction method which could extend the financial factors based on extreme gradient boosting regression tree algorithm (XGBoost). A prediction model which could derive financial factors based on wind power timing data was proposed. The application of XGBoost algorithm with high prediction accuracy and fast training speed in prediction could help the prediction model converge quickly. The relevant experiment was conducted for verification with the wind power data set of a wind farm in Inner Mongolia of China and that of Tennet in Germany. The results showed that taking R2 score as an example, the proposed method improved by about 14.71% compared with the benchmark method. The total time for modeling and prediction of the proposed method did not exceed 500 ms.
|
|
Received: 06 May 2022
Published: 09 May 2023
|
|
|
| Fund: 国家自然科学基金资助项目(61962045)；内蒙古自治区自然科学基金资助项目(2021LHMS06001, 2019MS03014)；内蒙古自治区高等学校科学研究项目(NJZY21321)；内蒙古水利发展基金资助项目(NSK202109)；内蒙古自治区关键技术攻关计划资助项目(2020GG0094)； 内蒙古自治区科技重大专项(2019ZD016) |
|
Corresponding Authors:
Li-min LIU
E-mail: wangys@imut.edu.cn;liulimin789@126.com
|
基于XGBoost扩展金融因子的风电功率预测方法
现有风电功率预测模型的主要输入特征包括气象数据和功率数据, 高精度气象数据获取困难、数据间潜在关系难以表示、预测模型收敛缓慢, 提出基于极端梯度提升回归树算法(XGBoost)扩展金融因子的超短期风电功率预测新方法，以及基于风电时序数据衍生金融因子的预测模型.采用具有较高预测准确率与较快训练速度的XGBoost算法进行预测, 使得预测模型快速收敛.在中国内蒙古某风电场的风电功率数据集与德国Tennet公司风电功率数据集上进行实验验证.实验结果表明,以R2score为例，所提方法与基准方法相比提升约14.71%. 所提方法中的建模与预测合计时间不超过500 ms.
关键词：
风力发电,
超短期风电功率预测,
梯度提升回归树,
XGBoost,
金融因子
|
|
| [1] |
钱政, 裴岩, 曹利宵, 等 风电功率预测方法综述[J]. 高电压技术, 2016, 42 (4): 1047- 1060
QIAN Zheng, PEI Yan, CAO Li-xiao, et al Overview of wind power prediction methods[J]. High Voltage Engineering, 2016, 42 (4): 1047- 1060
doi: 10.13336/j.1003-6520.hve.20160405021
|
|
|
| [2] |
国家能源局. 我国风电并网装机突破3亿千瓦[EB/OL]. [2021-11-30]. http://www.nea.gov.cn/2021-11/30/c_1310343188.htm.
|
|
|
| [3] |
刘芳, 汪震, 刘睿迪, 等 基于组合损失函数的BP神经网络风力发电短期预测方法[J]. 浙江大学学报:工学版, 2021, 55 (3): 594- 600
LIU Fang, WANG Zhen, LIU Rui-di, et al Short-term forecasting method of wind power generation based on BP neural network with combined loss function[J]. Journal of Zhejiang University: Engineering Science, 2021, 55 (3): 594- 600
|
|
|
| [4] |
李相俊, 许格健 基于长短期记忆神经网络的风力发电功率预测方法[J]. 发电技术, 2019, 40 (5): 426- 433
LI Xiang-jun, XU Ge-jian Wind power prediction method based on long short-term memory neural network[J]. Power Generation Technology, 2019, 40 (5): 426- 433
doi: 10.12096/j.2096-4528.pgt.19108
|
|
|
| [5] |
谢小瑜, 周俊煌, 张勇军, 等 基于W-BiLSTM的可再生能源超短期发电功率预测方法[J]. 电力系统自动化, 2021, 45 (8): 175- 184
XIE Xiao-yu, ZHOU Jun-huang, ZHANG Yong-jun, et al Ultra-short-term power generation prediction method of renewable energy based on W-BiLSTM[J]. Automation of Electric Power Systems, 2021, 45 (8): 175- 184
|
|
|
| [6] |
王依宁, 解大, 王西田, 等 基于PCA-LSTM模型的风电机网相互作用预测[J]. 中国电机工程学报, 2019, 39 (14): 4070- 4081
WANG Yi-ning, XIE Da, WANG Xi-tian, et al Prediction of wind turbine network interaction based on PCA-LSTM model[J]. Proceedings of the CSEE, 2019, 39 (14): 4070- 4081
|
|
|
| [7] |
CHENG W Y Y, LIU Y, BOURGEOIS A J, et al Short-term wind forecast of a data assimilation/weather forecasting system with wind turbine anemometer measurement assimilation[J]. Renewable Energy, 2017, 107: 340- 351
doi: 10.1016/j.renene.2017.02.014
|
|
|
| [8] |
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 Wei-sheng, WANG Zheng, DONG Cun, et al Current situation and error analysis of short-term wind power prediction technology in china[J]. Automation of Electric Power Systems, 2021, 45 (1): 17- 27
|
|
|
| [9] |
JU Y, SUN G Y, CHEN Q H, et al A model combining convolutional neural network and light GBM algorithm for ultra-short-term wind power forecasting[J]. Ieee Access, 2019, 7: 28309- 28318
doi: 10.1109/ACCESS.2019.2901920
|
|
|
| [10] |
FU Y W, HU W, TANG M L, et al. Multi-step ahead wind power forecasting based on recurrent neural networks [C]// IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC). Kota Kinabalu: IEEE, 2018: 217-222.
|
|
|
| [11] |
ZHANG Y, LI Y T, ZHANG G Y Short-term wind power forecasting approach based on Seq2Seq model using NWP data[J]. Energy, 2020, 213: 118371
|
|
|
| [12] |
SHARIFIAN A, GHADI M J, GHAVIDEL S, et al A new method based on Type-2 fuzzy neural network for accurate wind power forecasting under uncertain data[J]. Renewable energy, 2018, 120: 220- 230
doi: 10.1016/j.renene.2017.12.023
|
|
|
| [13] |
Do we really need deep learning models for time series forecasting? [EB/OL]. [2022-05-06]. https://arxiv.org/abs/2101.02118.
|
|
|
| [14] |
何龙. 《深入理解XGBoost: 高效机器学习算法与进阶》[M]. 北京: 机械工业出版社, 2020: 146-156.
|
|
|
| [15] |
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.
|
|
|
| [16] |
杨安, 蒋群, 孙钢, 等 金融技术指标的用电数据分析[J]. 计算机应用, 2022, 42 (3): 904- 910
YANG An, JIANG Qun, SUN Gang, et al Electricity data analysis of financial technical indicators[J]. Journal of Computer Applications, 2022, 42 (3): 904- 910
|
|
|
| [17] |
DING B Y, LI L, ZHU Y L, et al. Research on comprehensive analysis method of stock KDJ index based on K-means clustering [C]// 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019). Dalian: Atlantis Press, 2019: 484-491.
|
|
|
| [18] |
ALMEIDA R D, REYNOSOMEZA G, STEINER M T A. Multi-objective optimization approach to stock market technical indicators [C]// IEEE Congress on Evolutionary Computation (CEC). Vancouver: IEEE, 2016: 3670-3677.
|
|
|
| [19] |
ZHENG H, WU Y H A xgboost model with weather similarity analysis and feature engineering for short-term wind power forecasting[J]. Applied Sciences, 2019, 9 (15): 3019
doi: 10.3390/app9153019
|
|
|
| [20] |
王桂兰, 赵洪山, 米增强 XGBoost算法在风机主轴承故障预测中的应用[J]. 电力自动化设备, 2019, 39 (1): 73- 77
WANG Gui-lan, ZHAO Hong-shan, MI Zeng-qiang Application of XGBoost algorithm in fault prediction of fan main bearing[J]. Electric Power Automation Equipment, 2019, 39 (1): 73- 77
doi: 10.16081/j.issn.1006-6047.2019.01.011
|
|
|
| [21] |
刘波, 秦川, 鞠平, 等 基于XGBoost与Stacking模型融合的短期母线负荷预测[J]. 电力自动化设备, 2020, 40 (3): 147- 153
LIU Bo, QIN Chuan, JU Ping, et al Short-term bus load forecasting based on fusion of XGBoost and stacking models[J]. Electric Power Automation Equipment, 2020, 40 (3): 147- 153
doi: 10.16081/j.epae.202002024
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
