Non-intrusive load decomposition method

Abstract

The invention belongs to the technical field of electrical load decomposition, and particularly relates to a non-intrusive load decomposition method. In order to overcome the defect that a traditional differential evolution algorithm is adopted in an existing non-intrusive load monitoring process, and stagnation is prone to occurring when the problem of multi-extremum optimization is solved, the non-intrusive load decomposition method adopts the following technical scheme that the non-intrusive load decomposition method comprises the steps: step 1, establishing a load feature library; step 2, monitoring to obtain an actual total load current sequence, and constructing a differential total current sequence model by taking the minimum Euclidean distance as a target function; step 3, constructing an improved differential evolution algorithm by using a step progressive decrease type number progressive decrease mechanism; step 4, performing iterative optimization by applying an improved differential evolution algorithm to obtain an optimal time coefficient of each electric appliance; and step 5, determining the on-state and the on-time of the electric appliance according to the optimal time coefficient. The beneficial effect of the invention is that the on-state recognition rate of each electric appliance is improved.

Description

technical field [0001] The invention belongs to the technical field of electric load decomposition, and in particular relates to a non-invasive load decomposition method. Background technique [0002] Non-intrusive load monitoring (NILM) refers to the installation of monitoring equipment at the power inlet, and by monitoring the voltage, current and other signals there, the type and operation status of a single load in the load cluster can be analyzed and obtained. It only needs to install a non-intrusive device at the power inlet, which not only reduces hardware costs, but also improves user acceptance. Non-intrusive power load monitoring technology is an important part of the power management system and user energy management system, and it is also the direction for the current intelligent grid and home management to further improve. Compared with intrusive technology, non-intrusive technology has the advantages of user-friendliness, low economic cost, convenient installa...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the problem that the traditional differential evolution algorithm is used in the existing non-invasive load monitoring process, it is easy to stagnate when solving multi-extreme value optimization problems, and provides a non-invasive load decomposition method to improve the overall situation of the traditional differential evolution algorithm Convergence speed and robustness, improve recognition accuracy

Images