.png){kind=icon}
.png){kind=icon}
Return
Modeling multi-agent systems to simulate sensor-based Smart Roads
.png){kind=icon}
PRE
AI
DOI：10.1016/j.simpat.2019.101994.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Smart Roads are systems that are changing road traffic through the use of information in real time. They use sensor and actuator networks deployed on people and the surrounding environment. Such networks are complex systems with distributed configurations. This issue causes difficulties in their development and configuration. To alleviate these problems, simulations become a key tool. They provide controlled environments to develop and test components. However, the use of simulations has downsides. Their development usually demands multi-disciplinary groups, where misunderstandings due to different backgrounds are frequent. Model-Driven Engineering (MDE) can help to alleviate this kind of problems. This paper introduces a framework for the development of simulations of Smart Roads following the Model-Driven Architecture (a specific MDE approach). It extends an existing MDE framework for simulations of road traffic with specific elements for Smart Roads (e.g., sensors and services). Two different Multi-Agent Systems (MASs) are respectively modeled to address these issues. The proposed framework also provides two specific support tools: a code generator to transform the models into source code, and an agent-based simulation platform for road traffic. A case study illustrates how to adapt the produced model specifications to the specific requirements of the road traffic platform. These specifications are included into a simulation based on tracking vehicles using sensors. Promising results have been obtained showing the viability of the proposal.
Keywords:
Smart roads
Model-driven engineering
Multi-agent system
Model-driven architecture
Road traffic simulation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.6
Papers:
2.6K
Citations:
4.8K