Task Allocation Strategies: A Study with a Multi-Agents System in Fully Distributed Information Systems

• Félix F. Ramos Corchado Université de Technologie de Compiègne
• Liming Chen Université de Technologie de Compiègne
• Marc Bui Université de Technologie de Compiègne
• Didier Donsez Université de Technologie de Compiègne
• Pascal Faudemay Université de Paris VI

DOI: https://doi.org/10.5753/sbes.1996.24450

Resumo

In this paper we present some task allocation technics useful on Internet or other Wide Area Network (WAN). These technics are based on the cooperation of multi-agents organized in one community of Reactive agents and another of Allocator agents. Reactive agents represent services availables on the WAN such as Internet search engines. Allocator agents' task is allocate the queries that they receive from users. To take such a decision, Allocator agents cooperate sharing theirs informations about the state of Reactive agents. An Allocator agent is able to characterize the behaviour of Reactive agents by means of a knowledge model we developed. In order to facilitate the composition of complex services such as retrieval of multiple language documents, we also define another agent type we call Sub-contractor agent.

Palavras-chave: Load balancing, Agents, cooperation, document query

Referências

Geist (A.), elin (A.), and Dongarra (J.) et al. PVM: Parallel Virtual Machine: A Users guide and tutorial for Networked Parallel Computing. MIT press, 1994.

A. Shaerfadm Y. Shoham and M. Tennenholtz. Adaptive load balancing: A study in multi-agent learning. Artificial Intelligence Research, pages 475-500, February 1995.

BILLIONNET Alain, COSTA Marie-Christine, and SUTTER Alain. Les problèmes de placement dans les systèmes distribués. T.S.I, 8(4):307-337, 89.

B.Folliot. Gatos distributed task manager. Convention Unix in Paris, 89.

Andy Bond. Load sharing in a distributed environment. Technical Report CS-TR-92/1, Victoria University of Wellington, Wellington New Zeland PO Box 600, October 1992.

Bemon Carole. Conception et Evaluation d'une Plate-forme pur le Placement Dynamique de processus Communicants. PhD thesis, Université Paul Sabatier, IRIT Université Paul Sabatier 118 Route de Narbonne 31062 Toulouse Cedex, september 1995.

K.M. Chandy and J.E. Hewes. File allocation in distributed systèms. In Int. Symposium on Computers Performance, Modeling, Measurement and Evaluation, pages 10-13, Cambridge Mass, march 1976.

L. Chen, Didier Donsez, and P. Faudemay. U-doc: a research vehicle for hyper document retrieval on the internet. Technical report, Heudiasyc Université de Technologie de Compiègne, 1996.

K. Efe and B. Groseli. Minimizing control overheads in adaptive load sharing. In Proc. 9th Int. Conf. on Distributed Computing Systems, 89.

Michael R Genesereth and Richard E. Fikes. Knowledge Interchange Format Version 3.0. Computer Science Department of Stanford University, Stanford, California 94305, 1992.

Ferber. J and Jacopin. The framework of eco-problem solving. Decentraized Artificial Intelligence, pages 181-193, august 1991.

Ju Jiubin, XU Gaochao, and Yang Kun. An intelligent load balancer for workstation clusters. Operating System Review, 29(1):7-16, Janvier 1995.

Dag Johansen, Robert van Renesse, and Fred B. Sneider. An introduction to the tacoma distributed system. Technical Report 95-23, Institut of Mathematical and Physical Sciences if the University of Tromso, University of Tromso, n-9037 Tromso, Norway, June 1995.

Demazeau Y. Muller J.P. from reactive to intentional agents. Decentralized Artificial Intelligence, 223- 10, juin 91.

L.Chen, D. Donsez, P. Faudemay, L. Sonké, and P. Maillé. U-doc: Serveurs distribués d'hyper-documents normalisés en enviromements ouvers. projet 617 retenue et labellisé par le ministère de l'industrie á la suite de l'appel à proposition pour les autoroutes de l'information. Technical report, Université de Technologie de Compiègne, Universite de Paris VI, 1996.

Traian MUTEAN and El-Ghazali TALBI. Métodes de placement statique des processus sur architectures parallèles. Technique ex Science Informatiques, pages 355-373, mai 1991.

Andrea Shaerf, Yoav Shoham, and Moshe Tennenholz. Adaptive load balancing: A study in multi-agent learning. Journal of Artificial Intelligence Research, 2, mai 1995.

Narinder Singh. A common lisp api and facilitator for absi. Technical Report Logic-93-4, Computer Science Department of Stanford University, Stanford, California 94305, march 1994.

J.A. Stankovik. Stability and distributed scheduling algorithms. IEEE Trans. On Software Engineering, 11,85.

Andrew S. Tannenbaum, M. Frans Kaashoek, Robert Van Renesse, and Henri E. BAL. The amoeba distributed operating system. Computer Communication, 1991.

Salvatore T.March and Sangkyu. Allocating data and operations to nodes in distributed database design. IEEE Transactions on Knowledge and Data Engineering, 7(3):305-317, april 1995.