Method and device for identifying non-invasive power consumption load

Abstract

The invention relates to a method and device for identifying a non-invasive power consumption load. The method includes the steps of identifying a first current signal at a load power supply inlet; using a matched filter corresponding to a predefined load to identify the first current signal and obtaining the working state of the load connected with the load power supply inlet. According to the provided technical scheme, the first current signal is identified by the matched filter corresponding to the predefined load, and the working state of the load connected with the load power supply inletis obtained, so that a complicated characteristic extraction process is avoided, and the load identification accuracy is high.

Description

technical field [0001] The invention relates to the technical field of electric load identification, in particular to a non-invasive electric load identification method and device. Background technique [0002] In recent years, with the development of smart grid and power demand side management technology and the improvement of energy conservation awareness, more and more sensors and smart meters have been installed in the power network to obtain real-time data of the power grid, such as voltage, current, power After the real-time data are collected and processed, they become important information for power system load control and metering and charging, so as to realize the safe, economical and reliable operation of the power grid. [0003] The traditional load monitoring with intrusive design needs to install sensors on each electrical equipment. Although the measurement data is relatively accurate, the installation work needs to enter the load, which is very cumbersome. Th...

AI Technical Summary

Problems solved by technology

[0003] The traditional load monitoring with intrusive design needs to install sensors on each electrical equipment. Although the measurement data is relatively accurate, the installation work needs to enter the load, which is very cumbersome. Therefore, non-intrusive load monitoring is becoming more and more widely used. focus on

The load identification method is of great significance in non-invasive load monitoring technology. The existing identification method is based on the change of load characteristics to identify, the feature extraction steps are cumbersome and the complete data of independent loads cannot be obtained.

The function of the matched filter is equivalent to performing an autocorrelation operation on the input signal, and the decomposition and identification of the load based on the matched filter can reduce the computational complexity, but the autocorrelation operation of the matched filter is a time-domain calculation method, and its calculation amount is relatively large. Large, the efficiency of load identification is too low and the delay is too large

Images