An adaptive resource allocation scheme for large-scale distributed simulation system

The goal of this paper is to provide an optimal solution for Data Distribution Management (DDM) in large-scale distributed simulations. Until now, all existing DDM approaches have tried to make DDM more efficient in different ways; however none has been able to optimize performance. The main reason for this inability is that these approaches manipulate the data generated in a simulation without evaluating the size of it. We propose a novel resource allocation scheme, the Adaptive Resource Allocation Control scheme (ARAC). The ARAC scheme is designed to optimize resource allocations for local and distributed processing work at each federate according to the size of the simulation. Efficiency is achieved by applying the analysis results of a static probability model, which we call the Matching Model. Performance comparisons between the existing grid-based approaches and the new adaptive approach show that the new scheme is much more flexible in adapting to various simulation sizes and comes much closer to an optimal solution. The novelty of the ARAC scheme is that it is able to scale the size of a simulation and control the simulation itself by running it in the most appropriate mode to achieve the desired efficiency. As a final result, the optimum performance is best approached.