Abstract (EN)

This paper presents an agent-based approach to design a Transportation Regulation Support System (TRSS). Based on a multi-agent modeling of a urban transportation network, the objective of our approach is to integrate the functionalities of the existing information system with the functionalities of a decision support system. The TRSS monitors the network activity and adjusts itself to the environment changes, that is to say it automatically detects incoherent data (regulation under normal conditions) and tra c disturbances and then it automatically proposes solutions to optimize the tra c ow (regulation under disturbed conditions). To demonstrate our approach, a transportation regulation support system called SATIR (Système Automatique de Traitement des Incidents en Réseau- Automatic System for Network Incident Processing) is presented. SATIR has been tested on the Brussel transportation network (STIB). Lastly, we show how using the multi-agent paradigm opens perspectives regarding the development of new functionalities to improve the management of a bus network.