A non-invasive electrical appliance identification method based on boost model

Abstract

The invention discloses a non-intrusive electrical appliance identification method based on the Boost model, which comprises the following steps: 1. collecting data from electric meters by adopting unlabeled data collection; , and record the power data of the meter and the corresponding electrical label; 3. First, use the Bootstrap algorithm to expand the labeled set, and combine it with the unlabeled set to form a training set, and then use it to establish a classification model; 4. Collect power mutation events in real time, use the training A good model classifies it and displays the identified electrical consumer results to the user; 5. Add the new sample and new label in the pre-identification stage to the original labeled data set, and repeat steps 3 and 4; 6. Use a model that meets the accuracy requirements to identify electrical appliances, and feed back to users or demanders in real time; the invention can realize the identification of electrical appliances among residential users through the power data of the total electric meter and a small amount of training data.

Description

technical field [0001] The invention relates to the technical field of online electrical appliance identification, in particular to a non-invasive electrical appliance identification method based on a Boost model. Background technique [0002] Power load monitoring refers to the technology of collecting electrical parameters generated during load operation through smart meters, and then analyzing its operating status. For home users, load monitoring can enable users to know the time-sharing power, start and stop time of each type of electrical appliances, and guide electricity consumption behavior based on this information, so as to achieve the purpose of energy saving. For power companies, through the monitoring of household electricity consumption, a typical user data platform is established to carry out fine modeling, analysis, classification, and formulation of power consumption behaviors of different users, so as to realize the rational allocation of power resources. ...

AI Technical Summary

Problems solved by technology

Intrusively, sensors with digital communication functions are installed at the interface between each electrical appliance and the grid to monitor the operating status and power consumption of each electrical appliance. The advantage of this method is that the measurement is accurate, but the disadvantage is that it needs To install circuit facilities on electrical appliances, the installation work needs to enter the interior of the electrical appliances, which is difficult to implement and will affect normal production work. In the method, the model identified by the rated power has a large error, and often requires the reactive power data of the meter, while the model recognized by the instantaneous current change has too high a requirement for the sampling rate of the meter

Images