发电技术 ›› 2025, Vol. 46 ›› Issue (2): 326-335.DOI: 10.12096/j.2096-4528.pgt.23129

• 新能源 • 上一篇    

低温天气下考虑风机运行状态聚类的短期风电功率预测方法

张扬帆1, 李奕霖2, 叶林2, 付雪姣1, 王正宇1, 王耀函1   

  1. 1.华北电力科学研究院有限责任公司(国网冀北电力科学研究院),北京市 西城区 100018
    2.中国农业大学信息与电气工程学院,北京市 海淀区 100083
  • 收稿日期:2024-05-10 修回日期:2024-08-01 出版日期:2025-04-30 发布日期:2025-04-23
  • 作者简介:张扬帆(1987),男,硕士,工程师,研究方向为新能源发电运行技术,zhangyangfanhit@163.com
    叶林(1968),男,博士,教授,研究方向为电力系统运行与控制、新能源发电技术,本文通信作者,yelin@cau.edu.cn
  • 基金资助:
    华北电力科学研究院有限责任公司科技项目(KJZ2022060)

Short-Term Wind Power Prediction Method Considering Wind Turbine Operation Status Clustering Under Low-Temperature Conditions

Yangfan ZHANG1, Yilin LI2, Lin YE2, Xuejiao FU1, Zhengyu WANG1, Yaohan WANG1   

  1. 1.North China Electric Power Research Institution (State Grid Jibei Electric Power Research Institute), Xicheng District, Beijing 100018, China
    2.College of Information and Electrical Engineering, China Agricultural University, Haidian District, Beijing 100083, China
  • Received:2024-05-10 Revised:2024-08-01 Published:2025-04-30 Online:2025-04-23
  • Supported by:
    the Science and Technology Program of North China Electric Power Research Institute Co., Ltd(KJZ2022060)

摘要:

目的 低温天气给包含高比例风电等新能源的电力系统运行带来了挑战,提升低温天气下的短期风电功率预测精度,将为电力系统的调度运行提供有效的决策信息。为此,提出一种低温天气下考虑机组运行状态聚类的风电功率预测方法。 方法 利用机组运行状态与保护控制信息,采用模糊C均值(fuzzy C-means,FCM)聚类算法对风电机组进行聚类;提出一种基于支持向量机的风机运行状态分组预测方法,预测风机是否处于正常运行状态;采用集成学习中的LightGBM算法预测风机正常运行时的功率值;基于运行状态和功率值的预测结果,给出风电场总体输出功率。最后,以冀北某风电场为例进行分析,验证所提方法的有效性。 结果 所提方法充分利用风机低温保护控制行为特征,准确预测了风电机组的关键切机时间,并给出停机容量,有效地拟合了风电功率曲线变化规律,将风电功率预测精度提升至90%以上。 结论 所提方法可为电力调度控制提供有效预测信息,也为大风等其他极端天气下的短期风电功率预测提供了参考。

关键词: 新能源, 电力系统, 风电, 功率预测, 机组运行, 模糊C均值(FCM)聚类, 支持向量机, 电力调度控制

Abstract:

Objectives Low-temperature weather poses challenges to the operation of power systems with a high proportion of new energy, such as wind power. Improving the accuracy of short-term wind power prediction under low-temperature conditions will provide effective decision-making information for power system scheduling and operation. To address this, a wind power prediction method considering the clustering of unit operation status under low-temperature conditions is proposed. Methods The fuzzy C-means (FCM) clustering algorithm is used to cluster wind turbines based on their operation status and protection control information. Then, a prediction method based on support vector machine is proposed to predict whether the wind turbines are in normal operation status. The LightGBM algorithm in ensemble learning is employed to predict the power output of wind turbines under normal operation. Based on the prediction results of both operation status and power values, the overall wind power output of the wind farm is determined. Finally, a case study of a wind farm in northern Hebei is conducted to validate the effectiveness of the proposed method. Results By fully utilizing the characteristics of wind turbine protection control behaviors under low temperatures, the proposed method accurately predicts the critical shutdown time of wind turbines and provides the shutdown capacity. It effectively fits the variation patterns of wind power curves,which improves the prediction accuracy of the wind power to more than 90%. Conclusion The proposed method can provide reliable prediction information for power scheduling and control. Additionally, it can provide a reference for short-term wind power prediction under other extreme weather conditions, such as strong winds.

Key words: new energy, power system, wind power, power prediction, unit operation, fuzzy C-means (FCM)clustering, support vector machine, power scheduling and control

中图分类号: