Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms

Route planning for electric vehicles (EVs) is a critical challenge in sustainable transportation, as it directly addresses concerns about greenhouse gas emissions and energy efficiency. This study presents a novel approach that combines K-means clustering and GA optimization to create dynamic, real-...

Full description

Saved in:
Bibliographic Details
Main Authors: Tal Gaon, Yovel Gabay, Miri Weiss Cohen
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/3/97
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341954313158656
author Tal Gaon
Yovel Gabay
Miri Weiss Cohen
author_facet Tal Gaon
Yovel Gabay
Miri Weiss Cohen
author_sort Tal Gaon
collection DOAJ
description Route planning for electric vehicles (EVs) is a critical challenge in sustainable transportation, as it directly addresses concerns about greenhouse gas emissions and energy efficiency. This study presents a novel approach that combines K-means clustering and GA optimization to create dynamic, real-world applicable routing solutions. This framework incorporates practical challenges, such as charging station queue lengths, which significantly influence travel time and energy consumption. Using K-means clustering, the methodology groups charging stations based on geographical proximity, allowing for optimal stop selection and minimizing unnecessary detours. GA optimization is used to refine these routes by evaluating key factors, including travel distance, queue dynamics, and time, to determine paths with the fewest charging stops while maintaining efficiency. By integrating these two techniques, the proposed framework achieves a balance between computational simplicity and adaptability to changing conditions. A series of experiments have demonstrated the framework’s ability to identify the shortest and least congested routes with strategically placed charging stops. The dynamic nature of the model ensures adaptability to evolving real-world scenarios, such as fluctuating queue lengths and travel demands. This research demonstrates the effectiveness of this approach for identifying the shortest, least congested routes with the most optimal charging stations, resulting in significant advancements in sustainable transportation and EV route optimization.
format Article
id doaj-art-012f1938c9aa40f4ad9b24fd12b4413c
institution Kabale University
issn 1999-5903
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-012f1938c9aa40f4ad9b24fd12b4413c2025-08-20T03:43:31ZengMDPI AGFuture Internet1999-59032025-02-011739710.3390/fi17030097Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic AlgorithmsTal Gaon0Yovel Gabay1Miri Weiss Cohen2Department of Software Engineering, Braude College of Engineering, Karmiel 2161002, IsraelDepartment of Software Engineering, Braude College of Engineering, Karmiel 2161002, IsraelDepartment of Software Engineering, Braude College of Engineering, Karmiel 2161002, IsraelRoute planning for electric vehicles (EVs) is a critical challenge in sustainable transportation, as it directly addresses concerns about greenhouse gas emissions and energy efficiency. This study presents a novel approach that combines K-means clustering and GA optimization to create dynamic, real-world applicable routing solutions. This framework incorporates practical challenges, such as charging station queue lengths, which significantly influence travel time and energy consumption. Using K-means clustering, the methodology groups charging stations based on geographical proximity, allowing for optimal stop selection and minimizing unnecessary detours. GA optimization is used to refine these routes by evaluating key factors, including travel distance, queue dynamics, and time, to determine paths with the fewest charging stops while maintaining efficiency. By integrating these two techniques, the proposed framework achieves a balance between computational simplicity and adaptability to changing conditions. A series of experiments have demonstrated the framework’s ability to identify the shortest and least congested routes with strategically placed charging stops. The dynamic nature of the model ensures adaptability to evolving real-world scenarios, such as fluctuating queue lengths and travel demands. This research demonstrates the effectiveness of this approach for identifying the shortest, least congested routes with the most optimal charging stations, resulting in significant advancements in sustainable transportation and EV route optimization.https://www.mdpi.com/1999-5903/17/3/97electric vehicle routingdynamic recharging queueGenetic AlgorithmK-means
spellingShingle Tal Gaon
Yovel Gabay
Miri Weiss Cohen
Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms
Future Internet
electric vehicle routing
dynamic recharging queue
Genetic Algorithm
K-means
title Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms
title_full Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms
title_fullStr Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms
title_full_unstemmed Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms
title_short Optimizing Electric Vehicle Routing Efficiency Using K-Means Clustering and Genetic Algorithms
title_sort optimizing electric vehicle routing efficiency using k means clustering and genetic algorithms
topic electric vehicle routing
dynamic recharging queue
Genetic Algorithm
K-means
url https://www.mdpi.com/1999-5903/17/3/97
work_keys_str_mv AT talgaon optimizingelectricvehicleroutingefficiencyusingkmeansclusteringandgeneticalgorithms
AT yovelgabay optimizingelectricvehicleroutingefficiencyusingkmeansclusteringandgeneticalgorithms
AT miriweisscohen optimizingelectricvehicleroutingefficiencyusingkmeansclusteringandgeneticalgorithms