Zobrazit v EDS

Large-Scale Optimization of Electric Vehicle Charging Infrastructure

Uloženo v:
Podrobná bibliografie
Název: Large-Scale Optimization of Electric Vehicle Charging Infrastructure
Autoři: Li, Chuan, Zhao, Shunyu, Gauthier, Vincent, Moungla, Hassine
Přispěvatelé: Gauthier, Vincent
Zdroj: Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems. :725-728
Informace o vydavateli: ACM, 2024.
Rok vydání: 2024
Témata: • Information systems Large-Scale Optimization, CCS Concepts, EV Infrastructure Planning, Queuing Theory, Applied computing → Transportation, Smart Spatial Grid, Spatial Optimization, • Computing methodologies → Machine learning, [INFO] Computer Science [cs], Electric Vehicle Charging, Geospatial Data Processing, CCS Concepts Applied computing → Transportation • Computing methodologies → Machine learning • Information systems Large-Scale Optimization
Popis: The rapid adoption of electric vehicles (EVs) is driving increasing demand for efficient and strategically placed charging stations. While numerous studies have explored optimization methods for the placement of EV charging stations, most focus on smaller geographic areas, leaving the challenge of optimizing station distribution across larger regions unresolved. This paper presents a novel approach for optimizing both the placement and capacity of EV charging stations using the H3 spatial grid system and queuing theory. By leveraging the hexagonal structure of the H3 grid, we accurately model spatial data and analyze EV charging demands in both urban and non-urban areas. Queuing theory is employed to predict station utilization and optimize the allocation of charging points, minimizing user wait times and ensuring efficient resource distribution. The proposed method is adaptable to future growth in EV adoption and addresses infrastructure needs in both high-demand and underserved regions. This paper outlines the framework developed for the 13th SIGSPATIAL Cup (GISCUP 2024), which achieved top-5 performance. Results based on real-world data demonstrate the model's effectiveness in enhancing the spatial distribution of charging stations, improving accessibility and efficiency in EV infrastructure.
Druh dokumentu: Article
Conference object
Popis souboru: application/pdf
DOI: 10.1145/3678717.3700830
Přístupová URL adresa: https://hal.science/hal-04810316v1
https://hal.science/hal-04810316v1/document
https://doi.org/10.1145/3678717.3700830
Rights: URL: https://www.acm.org/publications/policies/copyright_policy#Background
Přístupové číslo: edsair.doi.dedup.....2e77268c6f37186dcda9e8f11d2e30f4
Databáze: OpenAIRE
Popis
Abstrakt:The rapid adoption of electric vehicles (EVs) is driving increasing demand for efficient and strategically placed charging stations. While numerous studies have explored optimization methods for the placement of EV charging stations, most focus on smaller geographic areas, leaving the challenge of optimizing station distribution across larger regions unresolved. This paper presents a novel approach for optimizing both the placement and capacity of EV charging stations using the H3 spatial grid system and queuing theory. By leveraging the hexagonal structure of the H3 grid, we accurately model spatial data and analyze EV charging demands in both urban and non-urban areas. Queuing theory is employed to predict station utilization and optimize the allocation of charging points, minimizing user wait times and ensuring efficient resource distribution. The proposed method is adaptable to future growth in EV adoption and addresses infrastructure needs in both high-demand and underserved regions. This paper outlines the framework developed for the 13th SIGSPATIAL Cup (GISCUP 2024), which achieved top-5 performance. Results based on real-world data demonstrate the model's effectiveness in enhancing the spatial distribution of charging stations, improving accessibility and efficiency in EV infrastructure.
DOI:10.1145/3678717.3700830