Efficient control of traffic networks is a complex but important task. A successful network management vitally depends on the abilities of the traffic light controllers to adapt to changing traffic situations. In this paper a control architecture for traffic nodes is presented that is inspired by the principles of organic computing. It allows a node to quickly adapt to changing traffic situations and enables it to autonomously learn new control strategies requiring only limited expert knowledge with respect to traffic control for operation. An learning classifier system (LCS) is used for the selection process, but - different from standard LCS systems - the generation of new classifiers is moved to a separate evolutionary algorithm that evaluates actions based on simulated results. Otherwise, the system would not be able to guarantee a minimum level of quality for the rules that are employed for controlling real traffic.
An organic architecture for traffic light controllers
Eine Organic-Computing-Architektur für Verkehrsampelsteuerung
2006
8 Seiten, 3 Bilder, 12 Quellen
Conference paper
English
Integrated Self-Organized Traffic Light Controllers for Signalized Intersections
ArXiv | 2020
|Civilian Air Traffic Controllers
NTIS | 1981
|Optimizing traffic light controllers by means of evolutionary algorithms
Tema Archive | 1998
|Air Traffic Control - US controllers - FAA lambasts controllers
Online Contents | 2005