Cloud-edge collaboration method for abnormal power consumption pattern recognition considering dynamic expression of information

被引：0
|
作者：
Liu H. [1 ]
Wang Y. [1 ]
Hu W. [1 ]
Xiao X. [1 ]
机构：
[1] College of Electrical Engineering, Sichuan University, Chengdu
来源：
Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2022年 / 42卷 / 07期
基金：
中国国家自然科学基金;
关键词：
abnormal power consumption recognition; cloud-edge collaboration; data compression; dynamic expression of information; similarity measurement;
D O I：
10.16081/j.epae.202204051
中图分类号：
学科分类号：
摘要：
Abnormal power consumption recognition is an important part of the power consumption check and the operation status identification of metering devices，and is of great significance to maintain the safe operation of power grid and protect the rights and interests of normal users. In order to recognize multiple power consumption patterns of users，existing methods tend to cause complicated calculation on the basis of ensuring recognition accuracy. While，simple calculation methods considering efficiency are difficult to accurately measure the similarity of different power consumption patterns，so it is difficult to give consideration to calculation efficiency and accuracy. In addition，uploading power consumption data to the cloud for centralized computing consumes a large amount of network bandwidth and computing resources，which further limits the application of anomaly recognition. Therefore，a cloud-edge collaboration method for abnormal power consumption pattern recognition considering the dynamic expression of information is proposed. According to the computing resources of the edge terminal and the cloud，the cooperative tasks are reasonably allocated to realize the cloud-edge collaboration recognition of abnormal power consumption. Aiming at the problem of limited computing power of edge servers，the dynamic compression and re-expression of power consumption data are carried out to reduce the data amount and ensure the accuracy of data information. After receiving the compressed data，the cloud takes the segmented weighted dynamic time warping distance as the basis for the similarity measurement of compressed data，and identifies abnormal power consumption based on the density clustering algorithm with adaptive parameter selection. The effectiveness of the proposed method is verified based on the actual data set. © 2022 Electric Power Automation Equipment Press. All rights reserved.
引用
收藏
页码：59 / 67
页数：8
相关论文
共 21 条
  • [1] Detection of non-technical losses using smart meter data and supervised learning［J］, IEEE Transactions on Smart Grid, 10, 3, pp. 2661-2670, (2019)
  • [2] ZHAO Wenqing, SHEN Zheji, LI Gang, Anomaly detection for power consumption pattern based on deep learning［J］, Electric Power Automation Equipment, 38, 9, pp. 34-38, (2018)
  • [3] LI Zixin, LI Chuan, LI Yingna, Reduced dimension of power consumption characteristicsand detection of electricity larceny by extreme learning machine［J］, Computer Applications and Software, 35, 12, pp. 179-186, (2018)
  • [4] CHEN Qixin, ZHENG Kedi, KANG Chongqing, Et al., Detection methods of abnormal electricity consumption behaviors：review and prospect［J］, Automation of Electric Power Systems, 42, 17, pp. 189-199, (2018)
  • [5] YUAN Xiangyu, ZHANG Penghe, XIONG Suqin, Et al., Research on identification method of abnormal power consumption based on logistic regression algorithm［J］, Electrical Measurement & Instrumentation, 58, 12, pp. 81-87, (2021)
  • [6] WANG X L, AHN S H., Real-time prediction and anomaly detection of electrical load in a residential community［J］, Applied Energy, 259, (2020)
  • [7] NAGI J, TIONG S K，, Et al., Nontechnical loss detection for metered customers in power utility using support vector machines［J］, IEEE Transactions on Power Delivery, 25, 2, pp. 1162-1171, (2010)
  • [8] JOKAR P，, ARIANPOO N, LEUNG V C M., Electricity theft detection in AMI using customers’ consumption patterns［J］, IEEE Transactions on Smart Grid, 7, 1, pp. 216-226, (2016)
  • [9] A tunable fraud detection system for advanced metering infrastructure using short-lived patterns［J］, IEEE Transactions on Smart Grid, 10, 1, pp. 830-840, (2019)
  • [10] TIAN Li, XIANG Min, Abnormal power consumption analysis based on density-based spatial clustering of applications with noise in power systems［J］, Automation of Electric Power Systems, 41, 5, pp. 64-70, (2017)
123