Distributed Detection System for Illegal Electricity Utilization Behavior in Smart Grid

Abstract

The invention discloses a distributed detection system for an illegal power utilization behavior of a smart power grid, and a detection method. The distributed detection system comprises a smart electricity meter data acquisition module, a smart electricity meter data transmission module, a smart electricity meter data storage module, a smart electricity meter data security authentication module and a smart electricity meter core computation module. According to the detection system and the detection method, global coverage of the smart power grid is realized; illegal power utilization detection is finished by a smart electricity meter; after system deployment is finished, compared with an original centralized detection system, the coverage range of the system is greatly expanded, emergency situations can be well dealt with, and the precision of computation and detection is relatively high.

Description

technical field [0001] The invention relates to a detection system for illegal electricity usage behavior in the field of smart grid data analysis, in particular to a distributed detection system and detection method for high-efficiency and fast-response smart grid illegal electricity usage behavior. Background technique [0002] The smart grid is a planning idea for the transformation of the next generation power grid. Its core significance is to introduce smart devices and update the original mechanical devices to make the global information exchange of the power grid more convenient and direct, and the regulation and configuration are also intelligent. Intuitive manifestations include the introduction of smart meters to realize two-way information interaction between power companies and grid users. [0003] Illegal use of electricity refers to the use of electricity by users not in accordance with the contract, generally including electricity fraud, electricity theft and ...

AI Technical Summary

Problems solved by technology

This method has considerable limitations: 1. For dense networks, the machine learning detection method takes a long time to run and is inefficient; 2. The detection accuracy is not high. According to the existing application examples, the accuracy is about 60%, and in the end it is still Requires data analyst to revalidate

3. The training sample is highly dependent, and its characteristic values ​​cannot be updated in time, so it is impossible to achieve "real-time" behavior detection

Images