High-Dimensional EV Charging Optimization: Leveraging APSO for Peak Load Management

In this study, we present an electric vehicle (EV) scheduling algorithm based on the Adaptive Particle Swarm Optimization (APSO) technique. The objective is to effectively manage a large-scale charging scenario. The scheduling problem involves numerous variables, including binary variables, represen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2025 International Conference on Intelligent Computing and Control Systems (ICICCS) s. 185 - 191
Hlavní autoři: Sriabisha, R., Aravindkumar, J.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 19.03.2025
Témata:
Data collection
Distribution Network
Electric Vehicle
Energy consumption
Heuristic algorithms
Microgrid
Optimization
Particle swarm optimization
Pricing
Scalability
Stability analysis
Strain
Sustainable development
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this study, we present an electric vehicle (EV) scheduling algorithm based on the Adaptive Particle Swarm Optimization (APSO) technique. The objective is to effectively manage a large-scale charging scenario. The scheduling problem involves numerous variables, including binary variables, representing the charging states and schedules of a fleet of EVs. Uncoordinated charging leads to simultaneous charging of all vehicles would result in a significant peak power demand, posing a strain on the power grid. To address this, the APSO algorithm effectively redistributes the charging times, achieving a notable reduction in peak demand in the optimal scenario. This reduction is facilitated by the algorithm's adaptive capabilities, which allow it to dynamically adjust to changing conditions and constraints, thereby optimizing the load distribution and enhancing grid stability. The simulation results demonstrate APSO's efficacy in addressing complex EV scheduling problems, contributing to more sustainable and efficient energy use in electric mobility.
DOI:10.1109/ICICCS65191.2025.10985256