A reinforcement learning approach for reducing traffic congestion using deep Q learning

Abstract Nowadays, traffic congestion is a significant issue globally. The vehicle quantity has grown dramatically, while road and transportation infrastructure capacities have yet to expand proportionally to handle the additional traffic effectively. Road congestion and traffic-related pollution ha...

Full description

Saved in:
Bibliographic Details
Main Authors: S M Masfequier Rahman Swapno, SM Nuruzzaman Nobel, Preeti Meena, V. P. Meena, Ahmad Taher Azar, Zeeshan Haider, Mohamed Tounsi
Format: Article
Language:English
Published: Nature Portfolio 2024-12-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-75638-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121856422117376
author S M Masfequier Rahman Swapno
SM Nuruzzaman Nobel
Preeti Meena
V. P. Meena
Ahmad Taher Azar
Zeeshan Haider
Mohamed Tounsi
author_facet S M Masfequier Rahman Swapno
SM Nuruzzaman Nobel
Preeti Meena
V. P. Meena
Ahmad Taher Azar
Zeeshan Haider
Mohamed Tounsi
author_sort S M Masfequier Rahman Swapno
collection DOAJ
description Abstract Nowadays, traffic congestion is a significant issue globally. The vehicle quantity has grown dramatically, while road and transportation infrastructure capacities have yet to expand proportionally to handle the additional traffic effectively. Road congestion and traffic-related pollution have increased, which is detrimental to society and public health. This paper proposes a novel reinforcement learning (RL)-based method to reduce traffic congestion. We have developed a sophisticated Deep Q-Network (DQN) and integrated it smoothly into our system. In this study, Our implemented DQL model reduced queue lengths by 49% and increased incentives for each lane by 9%. The results emphasize the effectiveness of our method in setting strong traffic reduction standards. This study shows that RL has excellent potential to improve both transport efficiency and sustainability in metropolitan areas. Moreover, utilizing RL can significantly improve the standards for reducing traffic and easing urban traffic congestion.
format Article
id doaj-art-52d9fe62acf34f8e9acae05e9e297d28
institution Kabale University
issn 2045-2322
language English
publishDate 2024-12-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-52d9fe62acf34f8e9acae05e9e297d282024-12-15T12:08:03ZengNature PortfolioScientific Reports2045-23222024-12-0114112010.1038/s41598-024-75638-0A reinforcement learning approach for reducing traffic congestion using deep Q learningS M Masfequier Rahman Swapno0SM Nuruzzaman Nobel1Preeti Meena2V. P. Meena3Ahmad Taher Azar4Zeeshan Haider5Mohamed Tounsi6Department of CSE, Bangladesh University of Business and TechnologyDepartment of CSE, Bangladesh University of Business and TechnologyDepartment of Electrical Engineering, Indian Institute of TechnologyDepartment of Electrical Engineering, National Institute of Technology JamshedpurCollege of Computer and Information Sciences, Prince Sultan UniversityCollege of Computer and Information Sciences, Prince Sultan UniversityCollege of Computer and Information Sciences, Prince Sultan UniversityAbstract Nowadays, traffic congestion is a significant issue globally. The vehicle quantity has grown dramatically, while road and transportation infrastructure capacities have yet to expand proportionally to handle the additional traffic effectively. Road congestion and traffic-related pollution have increased, which is detrimental to society and public health. This paper proposes a novel reinforcement learning (RL)-based method to reduce traffic congestion. We have developed a sophisticated Deep Q-Network (DQN) and integrated it smoothly into our system. In this study, Our implemented DQL model reduced queue lengths by 49% and increased incentives for each lane by 9%. The results emphasize the effectiveness of our method in setting strong traffic reduction standards. This study shows that RL has excellent potential to improve both transport efficiency and sustainability in metropolitan areas. Moreover, utilizing RL can significantly improve the standards for reducing traffic and easing urban traffic congestion.https://doi.org/10.1038/s41598-024-75638-0Traffic reductionRLSmart cityDQLQueue lengthRewards
spellingShingle S M Masfequier Rahman Swapno
SM Nuruzzaman Nobel
Preeti Meena
V. P. Meena
Ahmad Taher Azar
Zeeshan Haider
Mohamed Tounsi
A reinforcement learning approach for reducing traffic congestion using deep Q learning
Scientific Reports
Traffic reduction
RL
Smart city
DQL
Queue length
Rewards
title A reinforcement learning approach for reducing traffic congestion using deep Q learning
title_full A reinforcement learning approach for reducing traffic congestion using deep Q learning
title_fullStr A reinforcement learning approach for reducing traffic congestion using deep Q learning
title_full_unstemmed A reinforcement learning approach for reducing traffic congestion using deep Q learning
title_short A reinforcement learning approach for reducing traffic congestion using deep Q learning
title_sort reinforcement learning approach for reducing traffic congestion using deep q learning
topic Traffic reduction
RL
Smart city
DQL
Queue length
Rewards
url https://doi.org/10.1038/s41598-024-75638-0
work_keys_str_mv AT smmasfequierrahmanswapno areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT smnuruzzamannobel areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT preetimeena areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT vpmeena areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT ahmadtaherazar areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT zeeshanhaider areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT mohamedtounsi areinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT smmasfequierrahmanswapno reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT smnuruzzamannobel reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT preetimeena reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT vpmeena reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT ahmadtaherazar reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT zeeshanhaider reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning
AT mohamedtounsi reinforcementlearningapproachforreducingtrafficcongestionusingdeepqlearning