A dististributed simulation platform for cloud computing

Abstract

Advances in cloud services gave Cloud-Based Simulation (CBS) considerable attentions to obtain reliable, available, and scalable simulation models capable of executing on the Cloud. However, major challenges such as synchronization, virtualization, and multi-tenancy overhead overshadows use of CBS especially for distributed simulation. These challenges affect performance of parallel executions and thus limit the offered benefits. To overcome these issues, we propose a new platform Distributed Simulation for Could Computing (DSC) developed, to facilitate implementation and parallel execution of simulations models in the cloud. This platform has several layers including a middleware and an HPC platform called HPCaaS (HPC as a Service). The middleware acts as a simulation engine facilitating users to develop simulation models whereas HPCaaS makes them executable on a cloud platform. Along with their associate API, the proposed architecture enables simulation users to seamlessly interact with a cloud environment and receive benefits of the cloud for their applications.