电器与能效管理技术 ›› 2022, Vol. 0 ›› Issue (10): 81-86.doi: 10.16628/j.cnki.2095-8188.2022.10.014

• 检测与试验 • 上一篇    

基于生成对抗网络的窃电检测方法

朱月尧1, 魏星琦2, 张宸宇3   

  1. 1.国网江苏省电力有限公司 淮安供电分公司, 江苏 淮安 223002
    2.国网江苏省电力有限公司, 江苏 南京 210003
    3.国网江苏省电力有限公司电力科学研究院, 江苏 南京 211103
  • 收稿日期:2022-08-12 出版日期:2022-10-30 发布日期:2023-01-04
  • 作者简介:朱月尧(1990—),男,工程师,主要从事电能质量监测与控制研究。|魏星琦(1990—),男,工程师,主要从事电力系统分析与控制研究。|张宸宇(1989—),男,高级工程师,博士,主要从事智能保护及变电站综合自动化研究。

Power Theft Detection Method Based on Generative Adversarial Networks

ZHU Yueyao1, WEI Xingqi2, ZHANG Chenyu3   

  1. 1. Huai’an Power Supply Branch of State Grid Jiangsu Electric Power Co.,Ltd., Huai’an 223002, China
    2. State Grid Jiangsu Electric Power Co., Ltd., Nanjing 210003, China
    3. State Grid Jiangsu Electric Power Co., Ltd.Research Institute, Nanjing 211103, China
  • Received:2022-08-12 Online:2022-10-30 Published:2023-01-04

摘要:

针对智能电网背景下的窃电数据不平衡问题,提出了一种基于生成对抗网络(GAN)的窃电检测方法。生成器负责生成近似于真实的虚假样本去欺骗判别器,判别器负责区分真实样本和生成样本,通过二者的对抗训练来提高生成器的生成能力和判别器的判别能力,进而提高窃电检测的正确率与抗干扰能力。算例结果验证了所提算法的准确性和优越性。

关键词: 数据不平衡, 生成对抗网络, 窃电检测, 生成器, 判别器

Abstract:

To address the imbalance problem of power theft data in the context of the smart grid,a method of power theft detection based on generative adversarial networks (GAN) is proposed.The generator is responsible for generating false samples to deceive the discriminator,and the discriminator is responsible for distinguishing the real samples from the generated samples.The generation ability of the generator and the discrimination ability of the discriminator can be imporved through the adversarial training of the two,thus the accuracy and anti-interference ability of power theft detection can be improved.The accuracy and superiority of the proposed algorithm are validated by the example results.

Key words: data imbalance, generative adversarial networks(GAN), power theft detection, generator, discriminator

中图分类号: