Towards Large-Scale Cloud-Based Emergency Management Simulation "SimGenis Revisited"

Large-scale Crisis and Emergency Management Simulations (CEMS) often require huge computing and memory resources. Also a collaborative effort may be needed from researchers geographically distributed to better understand and study the simulated phenomena. The emergence of the cloud computing paradigm offers new opportunities for such simulations by providing on demand resources and enabling collaboration. This paper focuses on the scalability of emergency management simulation environments and shows how the migration to cloud computing can be effectively used for large-scale CEMS. Firstly, a generic deployment approach on a cloud infrastructure is introduced and applied to an existing agent-based simulator. Secondly, a deep investigation of the cloud-based simulator shows that the initial model remains stable and that the simulator is effectively scalable. Thirdly, a collaborative data analysis and visualization using Elastic-r is presented.