Effective route planning are essential for the growing number of electric vehicles (EVs) in order to enhance performance, reduce energy use, and shorten travel times. Some of particular challenges that EVs have in comparison to ICE cars include the availability of charging stations, the time required to charge an EV, and the limited capacity of its batteries. Three algorithms for EV routing are evaluated in this study: a modified version of Non-Dominated Sorting Genetic Algorithm II, the Bellman-Ford approach, and Dijkstra's algorithm. In their pursuit of minimizing travel time, traditional shortest-path algorithms often disregard energy efficiency and the ever-changing nature of traffic. The proposed NSGA-II-based method enhances multi-objective EV routing by making use of machine learning techniques to account for total route distance, journey duration, and energy use. It incorporates critical constraints including battery life, charging station accessibility, and energy consumption variability across a range of driving scenarios. The proposed NSGA-II is shown, through a large number of experimental results, to provide practical energy-efficient routing solutions, becoming much superior to conventional methods for electric vehicle transportation networks on a large scale.
Intelligent Route Planning for Electric Vehicles: Evaluating Multi-Objective Optimization Strategies
05.06.2025
475211 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Route and charging planning for electric vehicles: a multi-objective approach
Taylor & Francis Verlag | 2025
|A multi-objective route planning framework for automated and connected vehicles
TIBKAT | 2022
|A multi-objective route planning framework for automated and connected vehicles
DataCite | 2022
|