Bio-inspired Grid Information System with Epidemic Tuning
This paper proposes a bio-inspired approach for the construction of a Grid information system in which metadata documents that describe Grid resources are disseminated and logically reorganized on the Grid. A number of ant-like agents travel the Grid through P2P interconnections and use probability functions to replicate resource descriptors and collect those related to resources with similar characteristics in nearby Grid hosts. Resource reorganization results from the collective activity of a large number of agents, which perform simple operations at the local level, but together engender an advanced form of “swarm intelligence” at the global level. An adaptive tuning mechanism based on the epidemic paradigm is used to regulate the dissemination of resources according to users’ needs. Simulation analysis shows that the epidemic mechanism can be used to balance the two main functionalities of the proposed approach: entropy reduction and resource replication.
Unable to display preview. Download preview PDF.
- 2.Crespo, A., Garcia-Molina, H.: Routing indices for peer-to-peer systems. In: 22 nd International Conference on Distributed Computing Systems ICDCS’02, Vienna, Austria, pp. 23–33 (2002)Google Scholar
- 3.Dasgupta, P.: Intelligent Agent Enabled P2P Search Using Ant Algorithms. In: Proceedings of the 8th International Conference on Artificial Intelligence, Las Vegas, NV, pp. 751–757 (2004)Google Scholar
- 4.Eugster, P., et al.: Epidemic Information Dissemination in Distributed System. IEEE Computer 37(5), 60–67 (2004)Google Scholar
- 5.Forestiero, A., Mastroianni, C., Spezzano, G.: A Multi Agent Approach for the Construction of a Peer-to-Peer Information System in Grids. In: Proc. of the 2005 International Conference on Self-Organization and Adaptation of Multi-agent and Grid Systems, SOAS, Glasgow, Scotland (2005)Google Scholar
- 6.Petersen, K., et al.: Flexible Update Propagation for Weakly Consistent Replication. In: Proc. of the 16th Symposium on Operating System Principles, pp. 288–301. ACM, New York (1997)Google Scholar
- 7.Van Dyke Parunak, H., et al.: Pheromone Learning for Self-Organizing Agents. IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans 35(3) (2005)Google Scholar