Research on Smart Electric Meter Data Mining Technology Method for Line Loss Diagnosis of Low Voltage Station Area

DOI

10.2991/pntim-19.2019.59How to use a DOI?

Keywords

Component Management Line Loss, Data Mining; Layer-Based Analysis; Weighted LOF Algorithm; Outlier Analysis; Abnormal User Location

Abstract

Line loss can be divided into statistical line loss, technical line loss and management line loss according to structure. It not only refers to the energy loss in the form of heat energy, but also the management line loss caused by the electricity stealing behavior [1]. The calculation of power system line loss and the realization of system lean management are of great significance in guiding the reduction of energy conservation and the promotion of line loss management. To this end, in-depth analysis of the massive user data accumulated in the marketing automation process of the electricity information system in recent years, so as to establish a reasonable and efficient mathematical model of line loss analysis. By mining the useful information behind these data in smart electric meter, the abnormal power usage behavior detection of the user is realized, so as to achieve the purpose of preventing electric larceny and leakage and thereby reducing the line loss. This paper proposes a layer-based power line electric larceny detection method based on data mining technology .This method optimizes the traditional LOF algorithm and is a weighted LOF algorithm. By performing weighted outlier analysis on massive user data, the location of abnormal power users can be more efficiently completed.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yang Fuli
AU  - Hou Xingzhe
PY  - 2019/11
DA  - 2019/11
TI  - Research on Smart Electric Meter Data Mining Technology Method for Line Loss Diagnosis of Low Voltage Station Area
BT  - Proceedings of the 2019 International Conference on Precision Machining, Non-Traditional Machining and Intelligent Manufacturing (PNTIM 2019)
PB  - Atlantis Press
SP  - 287
EP  - 291
SN  - 2589-4943
UR  - https://doi.org/10.2991/pntim-19.2019.59
DO  - 10.2991/pntim-19.2019.59
ID  - Fuli2019/11
ER  -