Load identification method based on improved probabilistic neural network

Abstract

The invention discloses a load identification method based on an improved probabilistic neural network. The load identification method comprises steps of adopting a binary system to perform coding on a load type in an electricity usage network, establishing a coding library of load types, collecting an electric parameter of each load type, establishing a non-linear mapping relation between the electric parameter and the code of each load type, creating a probabilistic neural network, training the probabilistic neural network to obtain an error function, using the error function as a fitness function of a particle swarm algorithm, adopting the particle swarm algorithm to perform optimization on a smooth factor of the probabilistic neural network to obtain an optimal smooth factor, updating the probabilistic neural network according to the obtained optimal smooth factor to obtain an improved probabilistic neural network and performing recognition on the load type in the electricity usage network on the basis of the probabilistic neural network. The load identification method based on the improved probabilistic neural network can simultaneously identify multiple loads, improves speed of identifying a pernicious load under a multi-load mode, and can better realize recognition of restricted electric appliances and electricity usage control under a condition of multiple electric appliances.

Description

technical field [0001] The invention relates to the technical field of electrical load identification control, in particular to a load identification method based on an improved probabilistic neural network. Background technique [0002] At present, enterprises and college apartments generally have problems such as large power consumption, difficult management, and serious safety hazards. Especially in recent years, with the gradual expansion of the scale of colleges and universities and the continuous advancement of power electronics technology, the number of students has increased sharply, there are various types of power loads, and power management is complicated. Improper use of some high-power electrical appliances, such as fast heating, hair dryers, electric blankets, etc., can cause trips in the slightest, and fires in severe cases, endangering the personal and property safety of students. Therefore, the high-power resistive load belongs to the prohibited electrical ...

AI Technical Summary

Problems solved by technology

In terms of load identification technology, there are currently some solutions based on neural networks, such as the use of feedforward neural networks (BP neural networks), usually using conventional feedforward neural networks (BP neural networks) as pattern classifiers, but For the load identification problem of multi-feature input, the conventional feedforward neural network (BP neural network) has problems such as complex structure, long training time, slow convergence speed, and easy to fall into local optimum, resulting in long network training time and poor load type identification. rate is not high

Images