e_Buah Biblioteca Digital Universidad de Alcalá
Publicación
Artículo científico (JournalArticle)
Optimized Sensor Network and Multi-Agent Decision Support for Smart Traffic Light Management
One of the biggest challenges in modern societies is to solve vehicular traffic problems.
Sensor networks in traffic environments have contributed to improving the decision-making process
of Intelligent Transportation Systems. However, one of the limiting factors for the effectiveness
of these systems is in the deployment of sensors to provide accurate information about the traffic.
Our proposal is using the centrality measurement of a graph as a base to locate the best locations for
sensor installation in a traffic network. After integrating these sensors in a simulation scenario, we
define a Multi-Agent Systems composed of three types of agents: traffic light management agents,
traffic jam detection agents, and agents that control the traffic lights at an intersection. The ultimate goal
of these Multi-Agent Systems is to improve the trip duration for vehicles in the network. To validate
our solution, we have developed the needed elements for modelling the sensors and agents in the
simulation environment. We have carried out experiments using the Simulation of Urban MObility
(SUMO) traffic simulator and the Travel and Activity PAtterns Simulation (TAPAS) Cologne traffic
scenario. The obtained results show that our proposal allows to reduce the sensor network while
still obtaining relevant information to have a global view of the environment. Finally, regarding the
Multi-Agent Systems, we have carried out experiments that show that our proposal is able to improve
other existing solutions such as conventional traffic light management systems (static or dynamic) in
terms of reduction of vehicle trip duration and reduction of the message exchange overhead in the
sensor network., Universidad de Alcalá, Ministerio de Economía y Competitividad