Electrical load state identification method in home office environment

Abstract

The invention discloses an electrical load state identification method in a home office environment. In order to identify the working state of the electrical load more accurately and quickly, the transient power waveform TPW during switching of the electrical load (such as a refrigerator, an air conditioner, a water dispenser and the like) in home and office environments and the accurate label during load switching are firstly acquired so as to be used for load identification and algorithm performance evaluation. Then, aiming at difficulties existing in low-power and similar load identification, the invention provides a method for carrying out system clustering on the same kind of load TPW, a typical TPW template is selected, and the identification rate of the load is improved; and finally, in order to solve the difficulty of increasing load types, the invention provides a PSO algorithm to perform parameter optimization and determine the optimal combination of the typical TPW cluster number of the load, so the comprehensive performance of the load state identification algorithm is optimal. The method provided by the invention makes an important contribution to load state identification and intelligent power utilization in a home office environment.

Description

technical field [0001] The invention belongs to the technical field of non-intrusive load identification, and in particular relates to a method for identifying the status of electric loads in a home office environment. Background technique [0002] With the development of social economy, electricity has become one of the most widely used energy sources in today's society. In order to provide users with more reliable and green power and mitigate the impact of global warming and climate change, smart power consumption is becoming more and more important. In order to make better use of electric energy, it is first necessary to conduct load monitoring on electric loads. Load monitoring is to obtain user electricity consumption data and master detailed user load operating status and frequency of use. The key link of intelligent electricity consumption. [0003] Electric load monitoring methods can be roughly divided into two types: intrusive and non-invasive. Intrusive load mon...

AI Technical Summary

Problems solved by technology

[0006] The present invention aims at the problems of complex modeling of steady-state characteristics and low load recognition degree in the current method; low recognition accuracy of transient characteristics for similar equipment and low-power loads, etc., and proposes a method based on PSOSC-MDTW (Particle swarmoptimization-System Clustering-Multidimensional DTW) The load state identification algorithm is used to identify the state of the power load in the home office environment

Images