<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>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.</p>
</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.

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

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The distribution network structure is complex, the equipment is numerous, and the frequency of pattern and mode changes is high. These characteristics lead to...

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

Online veröffentlicht: 15. Juli 2022

Seitenbereich: 1027 - 1036

Eingereicht: 15. Feb. 2022

Akzeptiert: 22. Apr. 2022

DOI: https://doi.org/10.2478/amns.2022.2.0186

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

© 2023 Jie Yuan et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1

Figure 2

Figure 3

Figure 4

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

Online veröffentlicht: 15. Juli 2022

Seitenbereich: 1027 - 1036

Eingereicht: 15. Feb. 2022

Akzeptiert: 22. Apr. 2022

DOI: https://doi.org/10.2478/amns.2022.2.0186

SchlüsselwörterMachine learning, Mathematical and statistical methods, Power system, Graph-to-mode conversion, Ensemble

© 2023 Jie Yuan et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1

Figure 2

Figure 3

Figure 4

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