华东师范大学学报(自然科学版) ›› 2021, Vol. 2021 ›› Issue (6): 135-146.doi: 10.3969/j.issn.1000-5641.2021.06.014

• 计算机科学 • 上一篇    

基于鲁棒性随机分割森林算法的变压器损耗异常值检测

张国芳1(), 温丽丽1, 吴蒙1, 刘通宇2, 郑宽昀3, 黄福兴3, 袁培森2,*()   

  1. 1. 国网四川省电力公司, 成都 610094
    2. 南京农业大学 人工智能学院, 南京 210095
    3. 南瑞集团(国网电力科学研究院)有限公司, 南京 211106
  • 收稿日期:2020-09-11 出版日期:2021-11-25 发布日期:2021-11-26
  • 通讯作者: 袁培森 E-mail:zhanggf1261@sc.sgcc.com.cn;peiseny@163.com
  • 作者简介:张国芳, 女, 硕士, 高级工程师, 研究方向为电能量计量、综合能源管控与服务.E-mail: zhanggf1261@sc.sgcc.com.cn

Anomaly detection of transformer loss data based on a robust random cut forest

Guofang ZHANG1(), Lili WEN1, Meng WU1, Tongyu LIU2, Kuanyun ZHENG3, Fuxing HUANG3, Peisen YUAN2,*()   

  1. 1. State Grid Sichuan Electric Power Company, Chengdu 610094, China
    2. College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China
    3. Nanjing Automatic Research Insititute Group Corporation (State Grid Electric Power Research Institute), Nanjing 211106, China
  • Received:2020-09-11 Online:2021-11-25 Published:2021-11-26
  • Contact: Peisen YUAN E-mail:zhanggf1261@sc.sgcc.com.cn;peiseny@163.com

摘要:

在智能电网飞速发展的趋势下, 新型数字基础设施建设成为电力企业的核心业务之一, 电力企业数据的治理和智能化分析为平台运营、数据增值变现等商业模式创新提供了条件. 在电力数字化和智能化治理背景下, 使用鲁棒性随机分割森林算法实现变压器损耗数据的异常值智能化检测. 通过鲁棒性随机分割森林算法划分样本点以构建鲁棒性随机分割森林结构模型, 通过插入和删除样本点对结构复杂度的影响程度给定该样本点的异常值评分. 鲁棒性随机分割森林算法适用于实时损耗数据异常检测, 兼顾异常值检测效果和运行效率, 具有较高的可信度. 对真实变压器损耗数据集中进行异常值检测试验, 实验结果表明该算法高效、灵活, 相较于其他方法, 精确率、召回率及运行效率均有显著提升.

关键词: 鲁棒性随机分割森林, 异常值检测, 变压器损耗, 电力数据中台

Abstract:

With the rapid development of smart grids, the construction of new digital infrastructure has become one of the core businesses of power companies. Power companies’ governance and intelligent analytical capabilities enable opportunities for business model innovation, such as platform operation and value-added data realization. In the context of power digitization and intelligent governance, we use the robust random cut forest in this paper for transformer loss data anomaly intelligence detection. The algorithm divides sample points by random cutting to construct a random cut forest structure model by inserting and removing sample points in the structure; the anomaly score of a sample point is then given by the influence of complexity. This method is suitable for anomaly detection on real-time loss data and offers a high degree of credibility, effectiveness, and efficiency. An experiment of anomaly detection on real transformer loss data shows that the method is efficient and flexible. The accuracy, recall, and efficiency of the proposed method, moreover, is substantially better than alternatives.

Key words: robust random cut forest, anomaly detection, transformer loss, power data platform

中图分类号: