Non-invasive load decomposition based on improved differential evolution algorithm

Abstract

The invention relates to the technical field of non-intrusive load decomposition, in particular to a non-intrusive load decomposition method based on an improved differential evolution algorithm. A window function is designed for switching event detection and load steady-state operation time zone positioning. In order to solve the problem that the load identification rate of power load characteristics in a traditional NILD is not high, steady-state current harmonics of load equipment are selected as load identification characteristics. A load identification problem is converted into an objective function optimization problem, and optimization is performed based on a differential evolution algorithm (DE), and an improved DE algorithm of an adaptive cross factor is provided for solving the problems that a traditional DE is prone to falling into local optimization, and the convergence rate in the later period of evolution is low and the like. Experiments show that under different noise backgrounds, the load identification rate and the convergence rate of the improved DE algorithm based on steady-state current harmonics are obviously improved.

Description

Technical field [0001] The present invention relates to the technical field of non-invasive load decomposition, in particular to a non-invasive load decomposition method based on an improved differential evolution algorithm. Background technique [0002] Non-intrusive load decomposition is an important research content of the Intelligent Measurement System (AMI), which includes related knowledge such as event detection, signal processing, electricity consumption behavior analysis, combination optimization, and machine learning. Although the non-intrusive load decomposition has made great progress in recent years, it still faces huge challenges due to factors such as low load feature identification, sparse features, load sampling frequency, and filtering. [0003] Most NILD studies based on steady-state characteristics use active, reactive power, or a combination of the two as load characteristics. In this case, high-power load equipment may partially or overall cover the load chara...

AI Technical Summary

Problems solved by technology

Although non-intrusive load decomposition has made great progress in recent years, it still faces great challenges due to factors such as low load feature recognition, feature sparsity, load sampling frequency, and filtering.

[0003] Most of the NILD studies based on steady-state characteristics use active power, reactive power or a combination of both as load characteristics. In this case, high-power load equipment may partially or completely cover the load characteristic information of low-power load equipment, and Power ripple noise will also cover up low-power electrical appliances. In addition, for load equipment with similar electrical characteristics, there may be a phenomenon of feature overlap, which makes it impossible to identify between load equipment.

Images