Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning

In order to deal with dynamic traffic flow, adaptive traffic signal controls using reinforcement learning are being studied. However, most of the related studies are difficult to apply to the real field considering only mathematical optimization. In this study, we propose a reinforcement learning-ba...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jaun Gu, Minhyuck Lee, Chulmin Jun, Yohee Han, Youngchan Kim, Junwon Kim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	traffic signal optimization reinforcement learning adaptive traffic signal control multiple intersections Deep Q-network Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/7ed23d4e4a2b40009a8449538e8e862a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7ed23d4e4a2b40009a8449538e8e862a
record_format	dspace
spelling	oai:doaj.org-article:7ed23d4e4a2b40009a8449538e8e862a2021-11-25T16:35:19ZTraffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning10.3390/app1122106882076-3417https://doaj.org/article/7ed23d4e4a2b40009a8449538e8e862a2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10688https://doaj.org/toc/2076-3417In order to deal with dynamic traffic flow, adaptive traffic signal controls using reinforcement learning are being studied. However, most of the related studies are difficult to apply to the real field considering only mathematical optimization. In this study, we propose a reinforcement learning-based signal optimization model with constraints. The proposed model maintains the sequence of typical signal phases and considers the minimum green time. The model was trained using Simulation of Urban MObility (SUMO), a microscopic traffic simulator. The model was evaluated in the virtual environment similar to a real road with multiple intersections connected. The performance of the proposed model was analyzed by comparing the delay and number of stops with a reinforcement learning model that did not consider constraints and a fixed-time model. In a peak hour, the proposed model reduced the delay from 3 min 15 s to 2 min 15 s and the number of stops from 11 to 4.7 compared to the fixed-time model.Jaun GuMinhyuck LeeChulmin JunYohee HanYoungchan KimJunwon KimMDPI AGarticletraffic signal optimizationreinforcement learningadaptive traffic signal controlmultiple intersectionsDeep Q-networkTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10688, p 10688 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	traffic signal optimization reinforcement learning adaptive traffic signal control multiple intersections Deep Q-network Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	traffic signal optimization reinforcement learning adaptive traffic signal control multiple intersections Deep Q-network Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Jaun Gu Minhyuck Lee Chulmin Jun Yohee Han Youngchan Kim Junwon Kim Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
description	In order to deal with dynamic traffic flow, adaptive traffic signal controls using reinforcement learning are being studied. However, most of the related studies are difficult to apply to the real field considering only mathematical optimization. In this study, we propose a reinforcement learning-based signal optimization model with constraints. The proposed model maintains the sequence of typical signal phases and considers the minimum green time. The model was trained using Simulation of Urban MObility (SUMO), a microscopic traffic simulator. The model was evaluated in the virtual environment similar to a real road with multiple intersections connected. The performance of the proposed model was analyzed by comparing the delay and number of stops with a reinforcement learning model that did not consider constraints and a fixed-time model. In a peak hour, the proposed model reduced the delay from 3 min 15 s to 2 min 15 s and the number of stops from 11 to 4.7 compared to the fixed-time model.
format	article
author	Jaun Gu Minhyuck Lee Chulmin Jun Yohee Han Youngchan Kim Junwon Kim
author_facet	Jaun Gu Minhyuck Lee Chulmin Jun Yohee Han Youngchan Kim Junwon Kim
author_sort	Jaun Gu
title	Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
title_short	Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
title_full	Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
title_fullStr	Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
title_full_unstemmed	Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning
title_sort	traffic signal optimization for multiple intersections based on reinforcement learning
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/7ed23d4e4a2b40009a8449538e8e862a
work_keys_str_mv	AT jaungu trafficsignaloptimizationformultipleintersectionsbasedonreinforcementlearning AT minhyucklee trafficsignaloptimizationformultipleintersectionsbasedonreinforcementlearning AT chulminjun trafficsignaloptimizationformultipleintersectionsbasedonreinforcementlearning AT yoheehan trafficsignaloptimizationformultipleintersectionsbasedonreinforcementlearning AT youngchankim trafficsignaloptimizationformultipleintersectionsbasedonreinforcementlearning AT junwonkim trafficsignaloptimizationformultipleintersectionsbasedonreinforcementlearning
_version_	1718413086489051136

Traffic Signal Optimization for Multiple Intersections Based on Reinforcement Learning

Ejemplares similares