An intelligent agent for service selection in grid marketplace based on distributed genetic algorithm

Along with the fast increasing demands on computing power by researchers, grid marketplace becomes a,useful virtual marketplace that provides various mechanisms for grid service business. Generally, in grid,marketplace, a single grid service is most likely inadequate, to serve the customers' business needs, and it takes a selection of various grid services composed together to form, a composite service. In, this paper, we propose a new solution to service selection in grid marketplace based, on distributed genetic algorithm. and design an intelligent agent to implement the customers, requests. The distributed nature of the algorithm scales well in grid marketplace where there are a large number of service providers and their behaviors vary dynamically. Grid service selection is modeled as an optimization. process with the consideration of the relationships among the services. The experimental results show that the distributed genetic algorithm based service selection is able to find a set of services that meets the customer's QoS coastraints and, at the same time, optimizes the different QoS criteria.