A unified cloud-enabled discrete event parallel and distributed simulation architecture

Cloud simulation environments today are largely employed to model and simulate complex systems for remote accessibility variable capacity requirements. In this regard, scalability issues in Modeling Simulation (M\&S) computational requirements can be tackled through the elasticity of on-demand deployment. However, implementing a high performance cloud M\&S framework following these elastic principles is not trivial task as parallelizing distributing existing architectures challenging. Indeed, both parallel distributed developments have evolved separate ways. Parallel solutions has always been focused on ad-hoc solutions, while approaches, other hand, led definition standard frameworks like High Level Architecture (HLA) or influenced use technologies Message Passing Interface (MPI). Only few able evolve with current resilience computing hardware resources deployment, implementation Service (SaaS), albeit independently methods branch. paper, we present unified architecture enough flexibility deploy simulations low effort, without modifying underlying source code, reaching important speedups against sequential simulation, especially implementation. Our based Discrete Event System Specification (DEVS) formalism. The tested using xDEVS tool, Application Programming (API) DEVStone benchmark up eight nodes, obtaining maximum $15.95\times$ $1.84\times$, respectively.