基于KLDA- INFLO的继电保护整定数据异常识别方法
DOI:
作者:
作者单位:

国网山西省电力公司运城供电公司

作者简介:

通讯作者:

中图分类号:

基金项目:

国网山西省电力公司科技项目,名称:基于大数据辨识的配电网继电保护智能整定技术研究与应用,5205M02000xb。


Anomaly Detection Method for Protection Relay Setting based on KLDA- INFLO
Author:
Affiliation:

Yuncheng Power Supply Company of State Grid Shanxi Electric Power Company

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    当前电力系统存在规模不断扩大、功率输入来源不断增多、用电需求不断上升等现状,电网中出现电力运行扰动的频率不断增加,对继电保护稳定性提出了更高的要求。为实现对继电保护系统在运行过程中潜在扰动的及时应对,构建运行数据异常检测方法实施预警和分析。采用基于核函数的线性判别分析(Kernel Linear Discriminant Analysis,KLDA)模型,实现原始数据的降维处理从而达到降低运算负担、加快响应时间的效果。其次,结合基于被动式异常因子检测(Influenced Outlierness,INFLO)模型,依据运行整定参数正常数值范围,能够及时发掘异常节点,从而对异常运行状况做出快速反应。最后,以某地区配电网继保设施监测数据为例进行仿真分析,结果表明:该方法具有较高的异常检测性能,能够实现针对安全风险的自动校核与管控。

    Abstract:

    Nowadays, the scale of power systems is enlarging, the types of input power sources are increasing, and the demands are also raising. Hence, the disturbance in grids become more frequent which request higher reliability of operations of protection relay systems. To achieve the timely response for the potential disturbance in protection relay systems, this paper establishes anomaly detection method for warning and analyzing. Firstly, the Kernel Linear Discriminant Analysis model is utilized to decrease the computation burden via the dimensionality reduction in input data, and to accelerate the response. Then the Influenced Outlierness anomaly detection is designed. This model can find the outliers in time according to the common range of operation setting parameters, and thus to response swiftly to anomaly conditions. Finally, the empirical study which is based on the protection relay system in one distribution network is conducted. The results show that the performance of the proposed method is satisfying, and can be deployed to monitor or manage the countermeasures for potential risks.

    参考文献
    相似文献
    引证文献
引用本文
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
  • 收稿日期:2021-07-16
  • 最后修改日期:2021-08-03
  • 录用日期:2021-09-11
  • 在线发布日期:
  • 出版日期: