Adaptive Collaborative Agent-Based System for Crisis Management - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Adaptive Collaborative Agent-Based System for Crisis Management

Résumé

Agent-oriented approaches highlight logistic concepts which give structure to large distributed systems. We present an innovative cooperative agent-based model for Crisis Management Supply Chain in order to solve a highly-distributed delivery scheduling problem. The Supply Chain studied in this work is complex and composed of several elements such as transport means, suppliers, areas in need, resources, etc. The objective is to find an effective and quick solution for resources (food, water, clothes, etc.) distribution to the areas affected by the crisis to minimize damages and especially human losses. We propose an adaptive collaborative decision support system based on agents' cooperation and interaction. Our solution is an innovative architecture both dynamic and generic founded on the alliance between multi-agent systems and optimization tools. Depending on the studied crisis situation, agents can use the appropriate optimization tool. In the proposed solution, we involved several agents having various properties and varied roles. Inspired by the fact that agents are autonomous and intelligent entities, we consider in this work the ability of agents to have more than one role which changes according to the nature of the crisis and the needs of the studied situation.
Fichier principal
Vignette du fichier
IAT.pdf (629.63 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01716102 , version 1 (05-03-2018)

Identifiants

Citer

Sarah Ben Othman, Nesrine Zoghlami, Slim Hammadi, Hayfa Zgaya. Adaptive Collaborative Agent-Based System for Crisis Management. 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT), Aug 2014, Warsaw, Poland. ⟨10.1109/WI-IAT.2014.162⟩. ⟨hal-01716102⟩
212 Consultations
111 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More