An Edge Based Multi-Agent Auto Communication Method for Traffic Light Control
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.Keywords
This publication has 27 references indexed in Scilit:
- An introduction to Docker for reproducible researchACM SIGOPS Operating Systems Review, 2015
- The internet of things: a surveyInformation Systems Frontiers, 2014
- An efficient algorithm for computing traffic equilibria using TRANSYT modelApplied Mathematical Modelling, 2010
- Towards multi-agent reinforcement learning for integrated network of optimal traffic controllers (MARLIN-OTC)Transportation Letters, 2010
- Opportunities for multiagent systems and multiagent reinforcement learning in traffic controlAutonomous Agents and Multi-Agent Systems, 2008
- Reinforcement Learning for True Adaptive Traffic Signal ControlJournal of Transportation Engineering, 2003
- Q-learningMachine Learning, 1992
- Trends in distributed artificial intelligenceArtificial Intelligence Review, 1992
- Negotiating Task Decomposition and Allocation Using Partial Global Planning1989
- A Mathematical Theory of CommunicationBell System Technical Journal, 1948