Power load identification method and system based on machine learning

Abstract

The invention provides a power load identification method and system based on machine learning. Actually measured electrical parameter data including current, voltage, power and the like are taken asthe basis; basic electrical parameter data are unified in format, and on the basis of extracting, collecting, analyzing, concluding and training power load characteristics for a long time, the types of electrical appliances in use can be correctly identified under the condition that the overall basic electrical parameter data of a plurality of electrical loads in a period of time are known to include voltage, current, active power, reactive power and the like. Therefore, according to the machine learning model training method and system for power load identification provided by the invention,manual parameter adjustment is not needed; compared with traditional methods such as time domain waveform matching, feature point matching and spectral analysis, the method is high in matching accuracy, the feature parameters required for recognizing the power load can be learned autonomously and obtained automatically, and therefore the application range of the model is widened, and the accuracyof power load recognition is improved.

Description

technical field [0001] The present application relates to the technical field of electric load detection, and in particular to a machine learning-based electric load identification method and system. Background technique [0002] The power load feature is the rule that the active power and reactive power absorbed by the power load from the power supply of the power system change with the voltage of the load terminal and the system frequency; the power load feature is an important part of the power system; Electrical equipment plays an important role in the development of smart grid technology. [0003] The most commonly used methods for electric load identification are intrusive and non-intrusive identification methods. Among them, the intrusive identification method needs to establish a monitoring system to install sensors to each load. Although this method can directly obtain the measurement data of the load, the installation cost is high, the installation process is comp...

AI Technical Summary

Problems solved by technology

[0005] This application provides a method and system for identifying electrical loads based on machine learning to solve the technical problem that the artificially designed signal features in the existing methods require manual adjustment of parameters, resulting in low accuracy of electrical load identification

Images