Integrating NSGA-II and Q-learning for Solving the Multi-objective Electric Vehicle Routing Problem with Battery Swapping Stations

Document Type

Article

Source of Publication

International Journal of Intelligent Transportation Systems Research

Publication Date

1-1-2025

Abstract

Navigating the challenges of the Electric Vehicle Routing Problem with Battery Swapping Stations (EVRP-BSS), this work is centered on a multi-objective optimization task, simultaneously minimizing battery swap costs and energy consumption costs. Given the intricate nature of this problem and its real- world implications, we propose a particular solution methodology. Our hybridized approach introduces a learn-heuristic that leverages the Non-dominated Sorting Genetic Algorithm II (NSGA II) and the Q-learning algorithm. This method not only addresses the NP-hard complexity of the problem but also aims to improve the sustainability and cost-effectiveness of electric vehicle routing operations. In contributing a fresh perspective to the discourse on efficient and eco-friendly transportation, our study explores novel avenues for sustainable solutions. The experiments showed the good performance of the proposed approach for solving the EVRP-BSS.

ISSN

1348-8503

Publisher

Springer Science and Business Media LLC

Disciplines

Computer Sciences

Keywords

Battery swapping, Electric vehicle routing problem, Multi-objective optimization, NSGA-II, Q-learning

Scopus ID

05002721937

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS