Method for processing failures on adaptive basis in terminal of distribution network

Abstract

The invention relates to the technical field of power distribution and neural network and discloses a method for processing failures on an adaptive basis in a terminal of a distribution network. The method comprises the following steps: (a) constructing an input vector and an output vector for a neural network unit at the terminal of a distribution network; (b) initializing the neural network; (c) training the neural network by using a sample; (d) processing the failures of the distribution network by using the trained neural network unit; and (e) training the neural network by using a new sample to adapt to the change of distribution network when changes take place in the distribution network. The invention has the following beneficial effects: by using the ability of the neural network in self-learning and adaption, the terminal is capable of self-processing the complicated failures in a grid distribution network in various power supply manners and adapting to the changes in the structure of the distribution network, particularly realizing of processing emergent failures independent of a master station.

Description

technical field [0001] The invention relates to the fields of electric power distribution technology and neural network technology, in particular to a method for adaptively handling faults in distribution network terminals. Background technique [0002] Distribution network automation system remote terminal is a general term for various distribution remote terminals, distribution transformer remote terminals, medium voltage monitoring units (distribution automation and management system substations) and other equipment used in distribution network distribution circuits. The basic unit of a neural network is the neuron model. A neuron model is a mathematical model that simulates the structure and function of biological neurons, and is generally a nonlinear information processing unit with multiple inputs and single outputs. The basic forms of neural networks are forward network, feedback network, combined network and hybrid network. The most widely used neural network model...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems in the prior art, the present invention provides a method for adaptively handling faults in the distribution network terminal, which solves the problem that when the existing distribution network terminal is controlled locally, the terminal must rely on preset parameters, It can only be used for fixed and simple radiation network and ring network. When the distribution network changes, it cannot adapt to the change of the network, so that the distribution network terminal can handle the grid distribution network failure of complex multiple power supply channels. , and can adapt to changes in the distribution network

Images