Towards Domain-Model Optimized Deployment and Execution of Scientific Applications in Cloud Environments

Existing solutions for automatic scaling of applications in the cloud focus on the requirements of web services. A number of application servers is deployed, a load balancer is utilized to distribute the requests to these application servers, and new application servers are launched and configured when the requests exceed a certain capacity. However, the requirements for scaling scientific applications in a cloud are different. Often, these applications are used by a single scientist and the computational load is defined by the complexity of the model to be computed rather than by the number of users. In this paper, we present an alternative approach to scale scientific applications in the cloud. Hereby, the deployment scaling is driven by a domain model defined by the scientist.