A Multiattribute Combinatorial Exchange for Trading Grid Resources

The Computational Gris is a promising technology for providing access to distributed high-end computational capabilities. It enables the execution of complex and computationally demanding applications such as simulations or multimedia-renderings. However, one of the key problems in the Computational Grid is to decide which jobs are to be allocated to which resources at which time. In this context, the use of market mechanisms for scheduling and allocating Computational Grid resources is a promising approach to solve these problems. This paper describes the design of a mechanism for allocating and scheduling resources like processors or storage space having multiple attributes in Computational Grids according to the agents' bids. As such a clearing and pricing model for a multiattribute combinatorial exchange model is formulated, which supports bids on bundles, quality, and time attributes. We have evaluated the designed mechanism according to its computational tractability by means of a simulation.