Grid's Acquaintance-Based Multiagent Model of Distributed Meta-Scheduling

Computer grids are systems containing heterogeneous, autonomous and geographically distributed nodes. The management of these resources is the works of the meta-scheduler, who allocates work the nodes that are part of a grid, such as clusters, which in turn, have their own local schedulers. In this work we propose a new multi-agent distributed meta-scheduling model. Our model takes, on one hand, benefit from the flexibility of task allocation mode of acquaintances network to reduce the complexity of communication in decision-making, and secondly of the double auction sales to bring a mutual satisfaction between customers and resource providers. The Multi-Attribute Utility Theory (MAUT) is used for a more realistic gain of both. After simulation, through comparative performance analyzes, we show that our model has better contribution in terms of customer and supplier satisfaction than six current state-of-art meta-scheduling algorithms. Other qualitative assets as fault tolerance have to be mentioned.