Distribution network line meteorological prediction method based on wavelet neural network

Abstract

The invention relates to a distribution network line weather prediction method based on a wavelet neural network, and the method comprises the steps: constructing a topological structure of the wavelet neural network according to the data of a weather collection device, obtaining the data collected by a terminal weather collection device, carrying out the preprocessing of the data, taking the preprocessed data as the input of the wavelet neural network, and carrying out the prediction of the distribution network line weather. The output of the wavelet neural network is a meteorological prediction result. According to the method, the coupling relation among the four elements including the wind direction, the wind speed, the temperature and the humidity is fully considered, and hour-by-hour short-term prediction of the four meteorological elements is achieved through analysis of historical data. Technical reference is provided for realizing online monitoring and early warning of the galloping of the overhead line of the 10kV distribution network, the capability of resisting risks of the distribution network line is improved, and the method has practical significance and theoretical value. Meanwhile, the traditional wavelet neural network is optimized through the particle swarm optimization, the performance of the wavelet neural network is improved, and the prediction precision of the model is improved.

Description

technical field [0001] The invention belongs to the technical field of power distribution analysis, in particular to a weather prediction method for distribution network lines based on a wavelet neural network. Background technique [0002] In recent years, The phenomenon of galloping of overhead lines in distribution network occurs from time to time, causing a series of faults in distribution network lines, resulting in certain economic losses, and has gradually attracted the attention and attention of local power grid companies. It can be seen from the existing research data that the two crucial factors for the galloping of overhead lines are wind and icing, and icing is the result of the combined action of different meteorological conditions. Therefore, the meteorological conditions of the distribution network line are an important factor for the conductor galloping. With the advancement of science and technology, online monitoring of overhead lines with a large amount...

AI Technical Summary

Problems solved by technology

[0003] There is no relationship between different meteorological elements, and the analysis of any single element cannot fully mine the information hidden in the data, so that the accurate prediction of meteorological conditions cannot be realized

Images