Distributed text classification with an ensemble kernel-based learning approach
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
| Hi-index | 0.00 |
Grid technologies enable the sharing and coordinated use of diverse resources distributed all over the world. These resources are owned by different organizations having different policies and objectives, which need to be considered in making the resource allocation decisions. In such complex environments, market-based resource allocation protocols are a better alternative to the classical ones because they take into consideration the policies and preferences of both users and resource owners. The only suitable solution for investigating the effectiveness of these resource allocation protocols over a wide range of scenarios with reproducible results is to consider simulations. Thus, in this paper we present Mercatus, a simulation toolkit that facilitates the simulation of market-based resource allocation protocols. We describe the model and the structure of Mercatus, and present experimental results obtained by simulating five types of auction-based resource allocation protocols.