A community sharing intelligent charging pile site optimization method based on a knowledge graph
By constructing a knowledge graph of community shared charging station deployment and an improved MCLP maximum coverage site selection model based on knowledge graph methods, the problem of the inability to uniformly model the optimization methods of charging pile deployment in existing technologies is solved. This achieves accuracy in identifying charging demand and adaptability of power distribution capacity, thereby improving the utilization rate of charging resources.
Patent Information
- Application Number
- CN202610837779.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Filing Date
- 2026-06-11
- Publication Date
- 2026-07-17
AI Technical Summary
Existing methods for optimizing the deployment of shared charging stations in communities cannot uniformly model the relationship between vehicle charging and charging, the actual service status of existing charging stations, the permit status of parking space sharing, and the power distribution access capacity. This results in inconsistencies between the deployment results and the actual sharing and opening conditions and power distribution capacity, making it difficult to achieve refined optimization.
A knowledge graph-based approach is adopted to construct a knowledge graph for community shared charging station deployment. Combining the improved MCLP maximum coverage site selection model and the Lagrange relaxation solution mechanism, the relationships between vehicle charging, existing charging piles, parking space sharing, and power distribution access are established. Candidate deployment units are optimized through a three-state coverage matrix and the Lagrange penalty multiplier to generate a refined charging pile deployment scheme.
It improved the accuracy of charging demand identification and the adaptability of power distribution capacity, enhanced the utilization rate of community charging resources, ensured that the deployment plan matched the actual needs and power distribution capacity, and realized a closed-loop optimization process.
Smart Images
Figure CN122414724A_ABST