Active power distribution network weak node identification method and device

Abstract

The invention relates to an active power distribution network weak node identification method and device. The method comprises the steps of taking the data of a prediction day as the input of a wavelet neural network model, and obtaining the active power and reactive power of each phase of a distributed power supply of each node on the prediction day; determining an affine value corresponding to each phase active power and an affine value corresponding to each phase reactive power of the distributed power supply of each node on the prediction day based on each phase active power and each phasereactive power of the distributed power supply of each node on the prediction day and a prediction error mean value of a pre-established wavelet neural network model; obtaining an affine value corresponding to each phase voltage of each node on the prediction day based on the affine value corresponding to each phase active power and the affine value corresponding to each phase reactive power of the distributed power supply of each node on the prediction day; and identifying a weak node of the prediction day based on the affine value corresponding to each phase voltage of each node on the prediction day. According to the method, the prediction error of the distributed power supply is considered, and the accuracy of weak node identification is improved.

Description

technical field [0001] The invention relates to the technical field of power quality identification of active distribution networks, in particular to a method and device for identifying weak nodes of active distribution networks. Background technique [0002] With the continuous growth of electricity demand, the sharp shortage of traditional energy sources and the continuous development of the ubiquitous Internet of Things, the distribution network is developing towards high efficiency, flexibility, intelligence and sustainability. In recent years, due to the large-scale access of distributed power and the wide application of electric vehicles, the traditional unidirectional radial distribution network has gradually transformed into an active smart distribution network. However, the intermittent grid connection of high-penetration distributed power sources, especially photovoltaic power sources, has made problems such as rising short-circuit current, reducing power supply re...

AI Technical Summary

Problems solved by technology

For a smart distribution network containing distributed photovoltaic power, load fluctuations, distributed photovoltaic power output changes, and the continuous increase in the penetration rate of distributed photovoltaic power will cause the node voltage to fluctuate within an uncertain range. The traditional The deterministic weak node analysis method has been difficult to meet the requirements of weak node analysis in active smart distribution network

Images