Applied Mathematics and Nonlinear Sciences
Journal license

Journal

Applied Mathematics and Nonlinear Sciences


Volume
& Issue

Volume 7, Issue 2


Published
on

July 15, 2022


Pages

1027-1036


DOI

Article

Graphical Modular Power Technology of Distribution Network Based on Machine Learning Statistical Mathematical Equation

Check for updates


Authors

Jie Yuan Affiliation:
Information Center of Guizhou Power Grid Co., Ltd., Guiyang, 550002, China
, Yuan Ji Affiliation:
Information Center of Guizhou Power Grid Co., Ltd., Guiyang, 550002, China
, Yuman Yang Affiliation:
Information Center of Guizhou Power Grid Co., Ltd., Guiyang, 550002, China
, Junfeng Qian Affiliation:
Information Center of Guizhou Power Grid Co., Ltd., Guiyang, 550002, China
and Riyad Alshalabi Affiliation:
College of Administrative Sciences, Applied Science University, Bahrain


Abstract

The distribution network structure is complex, the equipment is numerous, and the frequency of pattern and mode changes is high. These characteristics lead to certain difficulties in power distribution automation operation and maintenance graph management. This paper adopts the mathematical statistics method of machine learning to analyze the multi-version hierarchical subscription mechanism of the distribution network graph. We conduct a breadth search on the distribution network graph to realize the automatic topology of the network. This paper implements a dynamic display system of distribution network monitoring information. The research results show that the graph-digital-analog integrated system has practical significance for data integration, application integration, and interoperability between systems.


Keywords

Machine learning, Mathematical and statistical methods, Power system, Graph-to-mode conversion, Ensemble, 97E60


Citation

Yuan, J., Ji, Y., Yang, Y., Qian, J., & Alshalabi, R. (2022). Graphical modular power technology of distribution network based on machine learning statistical mathematical equation. Applied Mathematics and Nonlinear Sciences, 7(2), 1027–1036. https://doi.org/10.2478/amns.2022.2.0186

Published by: Engineering Journals

Engineering Journals Logo