引用本文: | 赖 健,许志浩,康 兵,等.基于ISSA-SVC的配电网高损台区窃电检测方法研究[J].电力系统保护与控制,2024,52(12):104-112.[点击复制] |
LAI Jian,XU Zhihao,KANG Bing,et al.A detection method for electricity theft in a high loss station area of a distributionnetwork based on ISSA-SVC[J].Power System Protection and Control,2024,52(12):104-112[点击复制] |
|
本文已被:浏览 850次 下载 86次 |
码上扫一扫! |
基于ISSA-SVC的配电网高损台区窃电检测方法研究 |
赖健1,许志浩1,2,3,康兵1,2,王宗耀1,2,丁贵立1,2,袁小翠1,2 |
|
(1.南昌工程学院电气工程学院,江西 南昌 330099;2.江西省高压大功率电力电子与电网智能量测工程研究中心,
江西 南昌 330099;3.江西博微新技术有限公司,江西 南昌 330096) |
|
摘要: |
针对现有的基于机器学习的用户窃电行为检测方法检测效率和准确率不高等问题,提出一种基于改进麻雀搜索算法(improved sparrow search algorithm, ISSA)优化支持向量分类机(support vector classification, SVC)参数的ISSA-SVC窃电检测模型。首先,该模型通过分析台区每一天的线损率与窃电电量、窃电用户计量电量与窃电电量、窃电用户计量电量与线损电量、台区供电量与窃电电量、用户最近一天用电量和相邻几天用电量、具有相似特征用户用电量曲线的相关性提取用户窃电特征参量。其次,利用动态时间规整(dynamic time warping, DTW)方法计算得到它们的相关系数。最后,采用ISSA优化SVC惩罚参数C和核参数g,并对台区内窃电用户进行检测。仿真算例与实际电网数据分析表明,所提方法与传统的窃电检测方法相比,具有更高的效率和准确率。 |
关键词: 机器学习 窃电检测 用户窃电特征参量 相关系数 ISSA-SVC |
DOI:10.19783/j.cnki.pspc.231147 |
投稿时间:2023-09-04修订日期:2023-11-29 |
基金项目:国家自然科学基金项目资助(62001202) |
|
A detection method for electricity theft in a high loss station area of a distributionnetwork based on ISSA-SVC |
LAI Jian1,XU Zhihao1,2,3,KANG Bing1,2,WANG Zongyao1,2,DING Guili1,2,YUAN Xiaocui1,2 |
(1. School of Electrical Engineering, Nanchang Institute of Engineering, Nanchang 330099, China; 2. Jiangxi Engineering
Research Center of High Electricity Electronics and Grid Smart Metering, Nanchang 330099, China;
3. Jiangxi Booway New Technology Co., Ltd., Nanchang 330096, China) |
Abstract: |
Existing machine learning based user electricity theft detection methods have insufficient detection efficiency and accuracy. Thus an ISSA-SVC model based on the improved sparrow search algorithm (ISSA) to optimize the parameters of support vector classification (SVC) is proposed. First, the model analyzes the correlation between line loss rate and electricity theft, metered electricity consumption and electricity theft, metered electricity consumption and line loss, electricity supply and electricity theft, electricity consumption on the most recent day and adjacent days, and electricity consumption curves of the users with similar characteristics on each day of the station area to extract the characteristics of the users’ electricity theft. Secondly, it uses the dynamic time warping (DTW) algorithm to calculate their correlation coefficients. Finally, it uses ISSA to optimize the SVC penalty parameter C and kernel parameter g, and detect electricity theft users in the station area. Simulation examples and analysis of real grid data show that the proposed method has higher efficiency and accuracy than traditional power theft detection methods. |
Key words: machine learning electricity theft detection characteristics of the users’ electricity theft correlation coefficients ISSA-SVC |