Skip to main content
placeholder image

An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control

Journal Article


Download full-text (Open Access)

Abstract


  • With smart city infrastructures growing, the Internet of Things (IoT) has been widely

    used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control

    method based on reinforcement learning (RL) has expanded from one intersection to multiple

    intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm,

    which is an innovative adaptive global traffic light control method based on multi-agent reinforcement

    learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC

    algorithm combines multi-agent auto communication protocol with MARL, allowing an agent

    to communicate the learned strategies with others for achieving global optimization in traffic

    signal control. In addition, we present a practicable edge computing architecture for industrial

    deployment on IoT, considering the limitations of the capabilities of network transmission bandwidth.

    We demonstrate that our algorithm outperforms other methods over 17% in experiments in a real

    traffic simulation environment.

UOW Authors


  •   Wu, Qiang (external author)
  •   Wu, Jianqing (external author)
  •   Shen, Jun
  •   Yong, Binbin (external author)
  •   Zhou, Qingguo (external author)

Publication Date


  • 2020

Citation


  • Wu, Q., Wu, J., Shen, J., Yong, B. & Zhou, Q. (2020). An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control. Sensors, Online First 4291-1-4291-16.

Scopus Eid


  • 2-s2.0-85088916333

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=5294&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/4266

Has Global Citation Frequency


Start Page


  • 4291-1

End Page


  • 4291-16

Volume


  • Online First

Place Of Publication


  • Switzerland

Abstract


  • With smart city infrastructures growing, the Internet of Things (IoT) has been widely

    used in the intelligent transportation systems (ITS). The traditional adaptive traffic signal control

    method based on reinforcement learning (RL) has expanded from one intersection to multiple

    intersections. In this paper, we propose a multi-agent auto communication (MAAC) algorithm,

    which is an innovative adaptive global traffic light control method based on multi-agent reinforcement

    learning (MARL) and an auto communication protocol in edge computing architecture. The MAAC

    algorithm combines multi-agent auto communication protocol with MARL, allowing an agent

    to communicate the learned strategies with others for achieving global optimization in traffic

    signal control. In addition, we present a practicable edge computing architecture for industrial

    deployment on IoT, considering the limitations of the capabilities of network transmission bandwidth.

    We demonstrate that our algorithm outperforms other methods over 17% in experiments in a real

    traffic simulation environment.

UOW Authors


  •   Wu, Qiang (external author)
  •   Wu, Jianqing (external author)
  •   Shen, Jun
  •   Yong, Binbin (external author)
  •   Zhou, Qingguo (external author)

Publication Date


  • 2020

Citation


  • Wu, Q., Wu, J., Shen, J., Yong, B. & Zhou, Q. (2020). An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control. Sensors, Online First 4291-1-4291-16.

Scopus Eid


  • 2-s2.0-85088916333

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=5294&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/4266

Has Global Citation Frequency


Start Page


  • 4291-1

End Page


  • 4291-16

Volume


  • Online First

Place Of Publication


  • Switzerland