结合更新机制的电力系统暂态稳定评估研究
作者:
作者单位:

(1.三峡大学电气与新能源学院,湖北 宜昌 443002;2.新能源微电网湖北省协同创新中心,湖北 宜昌 443002;3.国网湖北省电力公司武汉供电公司,湖北 武汉 430013;4.国网山西省电力公司太原供电公司,山西 太原 030000)

通讯作者:

杨 超(1989—),男,硕士,讲师,主要从事研究方向为综合能源系统等方面的研究;E?mail:sanxiayc22@163.com

中图分类号:

TM712

基金项目:

湖北省自然科学基金(2022CFB825);国家自然科学基金项目(62233006,52007103);梯级水电站运行与控制湖北省重点实验室(三峡大学)开放基金(2023KJX06);电力系统智能运行与安全防御宜昌市重点实验室(三峡大学)开放基金(2020DLXY06)


Transient stability assessment of power system in combination with update mechanism
Author:
Affiliation:

(1. College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China; 2.Hubei Provincial Collaborative Innovation Center for New Energy Microgrid, Yichang 443002, China; 3.Wuhan Power Supply Company, State Grid Hubei Electric Power Co., Ltd., Wuhan 430013, China; 4.Taiyuan Power Supply Company, State Grid Shanxi Electric Power Co., Ltd., Taiyuan 030000, China)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    电力系统是一个时变的复杂系统。近年来,基于数据驱动的机器学习方法在电力系统暂态稳定评估领域得到了广泛应用。然而,当电力系统运行受到较大扰动发生工况变化时,机器学习模型需要根据新的运行数据进行训练,故其难以及时应对新拓扑结构下系统的暂态稳定情况评估。为解决该问题,首先,提出了一种模型更新机制,按照不同条件对模型进行更新;其次,引入了基于多面近端支持向量机(multisurface proximal support vector machine,MPSVM)的斜双随机森林(oblique double random forest with MPSVM,MPDRF)模型,并将其作为分类器对电力系统的稳定状态进行评估;最后,在新英格兰10机39节点系统上的进行仿真测试,验证该方法的有效性。研究结果表明,所提的结合更新机制的电力系统暂态稳定评估方法的评估性能优于普通方法的。

    Abstract:

    Power system is a time-varying complex system. In recent years, data-driven machine learning method has been widely used in the field of transient stability assessment of power system. However, when the power system is subjected to a large disturbance and the working condition changes, the machine learning model needs to be trained according to the new operating data. Thus, it is difficult to timely respond to transient stability assessment of the system under the new topology structure. To solve this problem, a model update mechanism is proposed in this paper, which updates the model according to different conditions. In addition, an oblique double random forest with multisurface proximal support vector machine (MPSVM) (MPDRF) model is introduced as a classifier to assess the stable state of power system. The simulation test on the New England 10-machine 39-bus system verifies the effectiveness of the proposed method. The results show that the method combined with update mechanism has high assessment performance, compared with the traditional method.

    参考文献
    相似文献
    引证文献
引用本文

刘颂凯,龚 潇,杨 超,等.结合更新机制的电力系统暂态稳定评估研究[J].电力科学与技术学报,2025,40(2):1-9.
LIU Songkai, GONG Xiao, YANG Chao, et al. Transient stability assessment of power system in combination with update mechanism[J]. Journal of Electric Power Science and Technology,2025,40(2):1-9.

复制
相关视频

分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 在线发布日期: 2025-06-06
文章二维码