An adaptive traffic light control system using reinforcement learning

Simple item page
dc.contributor.authorJearanaitanakij, Kietikul
dc.contributor.authorJamkhaw, Chanayut
dc.contributor.authorPuangpipat, Nattapat
dc.contributor.authorWorasrivisal, Tot
dc.date.accessioned2026-08-06T10:37:15Z
dc.date.available2026-08-06T10:37:15Z
dc.date.issued2022-07-01
dc.description.abstractTraffic signal control (TSC) is a challenging issue in managing an urban transportation system. A fixed time TSC is easy to implement but has drawbacks in such measures as flow rate, waiting time, and traffic density. The situation gets worse when the arrival rates of vehicles periodically change over time, which is usual in most urban cities. We propose adaptive reinforcement learning (RL) to manage TSC with varying vehicle arrival rates. Our objectives are to improve the averages of flow rate and waiting time and reduce the wasteful green light problem by considering the vehicle densities of the current lane and the downstream directions. Experiments were conducted by Simulation of Urban MObility (SUMO) under three traffic layouts and various vehicle arrival rates. The proposed method not only reduced on average traffic density, waiting time, and queue length, but also increased the average flow rate and average speed, relative to the other algorithms tested.
dc.identifier.citationSongklanakarin Journal of Science and Technology, 44(4), 914-922, 2022
dc.identifier.issn01253395
dc.identifier.other2-s2.0-85139220448
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/13295
dc.sourceSongklanakarin Journal of Science and Technology
dc.subjectadaptive green light time
dc.subjectreinforcement learning
dc.subjecttraffic signal control
dc.subjecttransportation
dc.subjectwasteful green light problem
dc.titleAn adaptive traffic light control system using reinforcement learning
dc.typeArticle

Files

Collections

Research