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

<p>In this study, the expressive ability and accuracy of the constraint rules for grid topological relationships are effectively improved by introducing the knowledge graph technology. The TransE model is used for training, focusing on the strategies to eliminate single-node voltage overruns in single-line and multi-line open scenarios, and the characteristic relationship between co-matching coefficients and structural robustness is deeply analyzed, aiming to improve the grid’’s interference resistance by optimizing the structural robustness. The results show that the single-line high-quality scheme has six effective solutions, including lines 28-29, 26-29, 26-28, 21-22, and 2-3. In the multi-line high quality scenario, there are 11 effective solutions, such as lines 28-29, 21-22, etc. Further analysis shows that the robustness of the grid structure is better and the spreading of the outage area is relatively slow in the event of a fault when the co-matching coefficients r are −0.22374 and −0.14575, respectively. In particular, when r = −0.22374, the grid’’s robustness remains above 0.3 even when the number of nodes exceeds 30. The comprehensive optimization framework proposed in this study is expected to provide more reliable and efficient topological relationship constraint rules in power systems, which will provide strong support for the operation and management of power grids, and significantly improve the stability and security of power systems.</p>
</abstract>

In this study, the expressive ability and accuracy of the constraint rules for grid topological relationships are effectively improved by introducing the knowledge graph technology. The TransE model is used for training, focusing on the strategies to eliminate single-node voltage overruns in single-line and multi-line open scenarios, and the characteristic relationship between co-matching coefficients and structural robustness is deeply analyzed, aiming to improve the grid’’s interference resistance by optimizing the structural robustness. The results show that the single-line high-quality scheme has six effective solutions, including lines 28-29, 26-29, 26-28, 21-22, and 2-3. In the multi-line high quality scenario, there are 11 effective solutions, such as lines 28-29, 21-22, etc. Further analysis shows that the robustness of the grid structure is better and the spreading of the outage area is relatively slow in the event of a fault when the co-matching coefficients r are −0.22374 and −0.14575, respectively. In particular, when r = −0.22374, the grid’’s robustness remains above 0.3 even when the number of nodes exceeds 30. The comprehensive optimization framework proposed in this study is expected to provide more reliable and efficient topological relationship constraint rules in power systems, which will provide strong support for the operation and management of power grids, and significantly improve the stability and security of power systems.

Optimization of constraint rules for power grid topological relationships based on knowledge graph techniques

Applied Mathematics and Nonlinear Sciences

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

In this study, the expressive ability and accuracy of the constraint rules for grid topological relationships are effectively improved by introducing the...

Optimization of constraint rules for power grid topological relationships based on knowledge graph techniques

Online veröffentlicht: 26. Feb. 2024

Seitenbereich: -

Eingereicht: 12. Jan. 2024

Akzeptiert: 19. Jan. 2024

DOI: https://doi.org/10.2478/amns-2024-0520

Schlüsselwörter
Knowledge graph, Grid topological relationships, Constraint rules, TransE model, Robustness

© 2024 Yu Wang et al., published by Sciendo

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

Optimization of constraint rules for power grid topological relationships based on knowledge graph techniques

Online veröffentlicht: 26. Feb. 2024

Seitenbereich: -

Eingereicht: 12. Jan. 2024

Akzeptiert: 19. Jan. 2024

DOI: https://doi.org/10.2478/amns-2024-0520

SchlüsselwörterKnowledge graph, Grid topological relationships, Constraint rules, TransE model, Robustness

© 2024 Yu Wang et al., published by Sciendo

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

Schlüsselwörter
Knowledge graph, Grid topological relationships, Constraint rules, TransE model, Robustness