Wind Power Interval Prediction Based on Fluctuation Trend Segmentation

被引：0
|
作者：
Han L. [1 ]
Yu X. [1 ]
Yu H. [1 ]
Wang C. [1 ]
Wang X. [1 ]
机构：
[1] School of Electrical Engineering, China University of Mining and Technology, Xuzhou
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2023年 / 47卷 / 18期
基金：
中国国家自然科学基金;
关键词：
dual-time segmentation; error cloud model; interval prediction; wind power;
D O I：
10.7500/AEPS20221118002
中图分类号：
学科分类号：
摘要：
The volatility of the wind power restricts the accuracy of its prediction. Therefore, based on the analysis of sequence changing trend for the wind power, an interval prediction method based on the fluctuation trend segmentation of the wind power is proposed. First, the average filtering algorithm and sliding window are applied to extract the power fluctuation trend and inflection point over the whole time period. Aiming at the problem that the traditional segmentation methods only consider the power change rate between adjacent inflection points, an improved dual-time segmentation method is proposed to obtain segmentation results. Then, considering the characteristics of power error in different periods, a segmented prediction method is proposed. k-means algorithm is applied to the fluctuation period and steady period to obtain the clustering results. The error interval of the steady period is obtained based on the clustering results of the steady period, and the error cloud model for the classification is established based on the clustering results of the fluctuation period, to obtain the error interval of the fluctuation period. And the prediction value of the deterministic prediction model is superimposed to obtain the interval prediction results of the whole time period. Finally, the wind power data from the Elia is utilized to conduct a case analysis, and the results indicate that the proposed method performs better in wind power interval prediction. © 2023 Automation of Electric Power Systems Press. All rights reserved.
引用
收藏
页码：206 / 215
页数：9
相关论文
共 30 条
  • [1] YE Lin, ZHAO Jinlong, LU Peng, Et al., Combined prediction of short-term wind power considering correlation of meteorological features and fluctuation process［J］, Automation of Electric Power Systems, 45, 4, pp. 54-62, (2021)
  • [2] YUE Xiaoyu, PENG Xiangang, LIN Li, Short-term wind power forecasting based on whales optimization algorithm and support vector machine［J］, Proceedings of the CSU-EPSA, 32, 2, pp. 146-150, (2020)
  • [3] CHEN Q H，, Et al., A model combining convolutional neural network and LightGBM algorithm for ultra-short-term wind power forecasting［J］, IEEE Access, 7, pp. 28309-28318, (2019)
  • [4] SU Xiangjing, ZHOU Wenxin, LI Chaojie, Et al., Interpretable offshore wind power output forecasting based on long short-term memory neural network with dual-stage attention［J］, Automation of Electric Power Systems, 46, 7, pp. 141-151, (2022)
  • [5] DONG Xiaochong, SUN Yingyun, PU Tianjiao, Et al., Ultra-short-term probabilistic forecasting of wind power based on temporal mixture density network［J］, Automation of Electric Power Systems, 46, 14, pp. 93-100, (2022)
  • [6] ZHOU Xiaolin, TONG Xiaoyang, Ultra-short-term wind power combined prediction based on CEEMD-SBO-LSSVR［J］, Power System Technology, 45, 3, pp. 855-864, (2021)
  • [7] WU Wenzu, QIAO Ying, LU Zongxiang, Et al., Methods and prospects for probabilistic forecasting of wind power ［J］, Automation of Electric Power Systems, 41, 18, pp. 167-175, (2017)
  • [8] DAI Jianfeng, YAN Cheng, TANG Yi, Hybrid forecasting model of ultra-short-term wind speed in wind farm based on time series residual probability［J］, Power System Technology, 47, 2, pp. 688-699, (2023)
  • [9] WU Haotian, SUN Rongfu, LIAO Siyang, Et al., Short-term wind power probability forecasting method based on improved meteorological clustering and classification［J］, Automation of Electric Power Systems, 46, 15, pp. 56-65, (2022)
  • [10] Fang LIU, PAN Yi, LIU Hui, Et al., Piecewise exponential distribution model of wind power forecasting error ［J］, Automation of Electric Power Systems, 37, 18, pp. 14-19, (2013)
123