Particle swarm principle-based power distribution network data preprocessing method adopting big data clustering

Abstract

The invention discloses a particle swarm principle-based power distribution network data preprocessing method adopting big data clustering, and belongs to the field of power distribution network reliability prediction. For the normalized power distribution network data, a clustering number selection mechanism which takes a bending moment method as a main method and takes a concave-convex coefficient method is adopted as an auxiliary method to obtain an optimal clustering number of a sample; after clustering analysis is carried out on the samples, abnormal value identification standards of upper and lower critical graphs are adopted to delimit diagnosis thresholds; if the distance between the sample and the clustering center is greater than a diagnosis threshold,a judgment is made that thesample is an outlier sample and removed. further, de-noised sample data is obtained; Potential rule of the power distribution network fault is predicted by adopting the sample data subjected to de-noising. Not only is the defect that a bending moment method and a concave-convex coefficient algorithm are easy to fall into a local extreme value overcome, but also global optimization of a particle swarm algorithm is maintained, and convergence speed of a bending moment method and a concave-convex coefficient algorithm is relatively high; the invention has the advantages of being good in denoisingeffect and high in sorting accuracy and effectiveness.

Description

technical field [0001] The invention belongs to the field of reliability prediction of distribution networks, and in particular relates to a distribution network data preprocessing method based on particle swarm principle using big data clustering. Background technique [0002] In recent years, the State Grid Corporation of China has intensified the transformation of distribution network automation and deepened the promotion and application of distribution automation systems. And the protection signal of the automatic switch, automatically judge the fault area, send a prompt signal to the control personnel or automatically complete the fault isolation and restore power supply, which improves the reliability of power supply and the quality of transmission. [0003] The power system is a unified whole of production, transmission, distribution, and consumption of electric energy, and any power system failure will affect users. According to statistics, more than 80% of user fai...

AI Technical Summary

Problems solved by technology

Aiming at the shortcomings of the bending moment method and the concave-convex coefficient method in the selection of the optimal N value of clustering at present, the particle swarm algorithm is combined with the bending moment method and the concave-convex coefficient algorithm, and the bending moment method is the main method, and the concave-convex coefficient method is supplemented The selection mechanism of the number of clusters, and simultaneously output the optimized distribution network data that eliminates outliers

Images