Servicing Provisioning for HLA-Based Distributed Simulation on the Grid

Abstract

Modeling and simulation permeate all areas of business, science and engineering. With the increase in the scale and complexity of simulations, large amounts of computational resources are required, and provisioning of the services is becoming increasingly difficult. The grid provides a platform for coordinated resource sharing and application development and execution. In this paper, we focus on extending the high level architecture (HLA) to the grid. More specifically, we propose a distributed simulation framework, called HLAGrid. The framework uses a Federate-Proxy-RTI architecture, which allows resources on the grid to be utilized on demand by using grid services. The architecture also supports federation discovery, security of the simulator logic, and flexible federation construction, such as hierarchical federations. The architecture hides the heterogeneity of the simulators, simulators' execution platforms, and how the simulators communicate with the RTI. All interfaces used in the framework comply with the standard HLA interface specification, which provides reusability to simulators. A prototype of the framework is implemented using DMSO's RTI 1.3NG version 6 and the grid system runs the Globus toolkit.