Non-invasive load monitoring method

Abstract

The invention discloses a non-invasive load monitoring method. The non-invasive load monitoring method comprises an equipment classification prediction sub-process, a new equipment identification sub-process and a classifier self-training sub-process. Compared with the prior art, the novel non-invasive load detection frame body has the following beneficial effects that on the basis of a traditional non-invasive load monitoring frame, the novel non-invasive load detection frame body is innovatively provided. Under the framework, firstly, collected high-frequency current and voltage data are effectively preprocessed, the data density is expanded through cleaning, linear filling and interpolation, and the integrity, accuracy and usability of the data are guaranteed. Through mining equipment characteristics, a multi-dimensional characteristic value which can represent an electric equipment operation mark is calculated and extracted. Different classifier models are considered, the random forest classifier model with the best effect is finally established for classification and recognition, the recognition accuracy is high, and the model robustness is high.

Description

technical field [0001] The invention relates to the field of load detection, in particular to a non-invasive load monitoring method. Background technique [0002] In recent years, due to the high cost and low efficiency of the traditional power load monitoring method, its application has been greatly restricted. The non-intrusive load monitoring system (non-intrusive load monitoring, NILM) technology only needs to install a Sensors monitor the working status of each or each type of electrical equipment inside the user by collecting and analyzing the user's electricity consumption characteristics such as current and voltage, and have been extensively studied. [0003] The architecture of traditional non-invasive research mainly includes data acquisition, data preprocessing, feature extraction, classifier prediction, and classification results. This kind of system architecture usually needs to establish a device library in advance, and perform data collection, data preprocess...

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, the traditional non-intrusive load monitoring system architecture has limitations and cannot cope with complex equipment replacement and changes.

Images