Agent-based modeling within a cyberinfrastructure environment: A service-oriented computing approach

Agent-based models (ABM) allow for the bottom-up simulation of dynamics in complex adaptive spatial systems through the explicit representation of pattern-process interactions. This bottom-up simulation, however, has been identified as both data-and computing-intensive. While cyberinfrastrucutre provides such support for intensive computation, the appropriate management and use of cyberinfrastructure (CI)-enabled computing resources for ABM raise a challenging and intriguing issue. To gain insight into this issue, in this article we present a service-oriented simulation framework that supports spatially explicit agent-based modeling within a CI environment. This framework is designed at three levels: intermodel, intrasimulation, and individual. Functionalities at these levels are encapsulated into services, each of which is an assembly of new or existing services. Services at the intermodel and intrasimulation levels are suitable for generic ABM; individual-level services are designed specifically for modeling intelligent agents. The service-oriented simulation framework enables the integration of domain-specific functionalities for ABM and allows access to high-performance and distributed computing resources to perform simulation tasks that are often computationally intensive. We used a case study to investigate the utility of the framework in enabling agent-based modeling within a CI environment. We conducted experiments using supercomputing resources on the TeraGrid - a key element of the US CI. It is indicated that the service-oriented framework facilitates the leverage of CI-enabled resources for computationally intensive agent-based modeling.