Determination of the optimal sizes and locations of hydrogen refueling stations for deploying hydrogen locomotives using multi-objective particle swarm optimization

This study presents a multi-objective, capacitated flow refueling location model aimed at identifying the optimal locations and capacities of hydrogen refueling stations (HRS) to support the deployment of hydrogen-powered passenger trains in the Northeast Frontier Railway (NFR) region of Assam, Indi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Soft computing (Berlin, Germany) Jg. 29; H. 23-24; S. 5971 - 5987
Hauptverfasser: Sarma, Upasana, Ganguly, Sanjib
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2025
Springer Nature B.V
Schlagworte:
Alternative energy
Artificial Intelligence
Computational Intelligence
Control
Costs
Engineering
Evolutionary algorithms
Fuel cells
Hydrogen
Hydrogen production
Infrastructure
Integer programming
Locomotives
Mathematical Logic and Foundations
Mechatronics
Multiple objective analysis
Optimization
Particle swarm optimization
Passenger trains
Planning
Railway stations
Refueling
Robotics
Traffic flow
Trains
Vehicles
Binary particle swarm optimization
Hydrogen refueling station
Multi-objective optimization
Railway planning
Strength Pareto evolutionary algorithm 2
ISSN:1432-7643, 1433-7479
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This study presents a multi-objective, capacitated flow refueling location model aimed at identifying the optimal locations and capacities of hydrogen refueling stations (HRS) to support the deployment of hydrogen-powered passenger trains in the Northeast Frontier Railway (NFR) region of Assam, India. The model simultaneously minimizes two key objectives: the total cost of ownership and the average refueling cost over a specified planning horizon. The analysis assumes centralized hydrogen production for the initial deployment phase and considers existing intercity railway stations in NFR as candidate sites for HRS installation. Optimization is conducted for three scenarios, each with different HRS capacity levels. Real-time intercity railway traffic data from NFR is used as input, and the optimization problem is solved using a Strength Pareto Evolutionary Algorithm 2-based Multi-Objective Binary Particle Swarm Optimization (SPEA2-based-MOBPSO) technique. The resulting Pareto fronts provide a range of optimal HRS layout configurations, highlighting trade-offs between infrastructure investment and operational efficiency.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1432-7643
1433-7479
DOI:10.1007/s00500-025-10847-x