Skip to Main Content
This paper presents CAMELotGrid, a grid-based cellular automata problem solving environment (PSE) for the modelling and simulation of complex phenomena, which uses a biologically inspired approach to allow the users to design grid applications through being not experts in grid computing. The approach is inspired to an autonomic computing paradigm defined by IBM with the goal to create computer systems that manage themselves in accordance with high-level guidance specified by users, in the same way the autonomic nervous system regulates the body systems without conscious input from the individual. The middleware architecture of CAMELotGrid is designed on top of the existing grid middleware and supports dynamic performance adaptation of the cellular application without any user intervention. The user must only specify, by global criteria, the high level policies and submit the application for execution over the grid. The CAMELotGrid architecture is based on a performance model that provides an accurate estimate of the performance of the cellular application on a specific collection of grid resources, a monitoring mechanism and a set of rules for interrupting and remapping an application execution when performance falls below acceptable levels. We also provide experimental validation of our approach for a cellular landslide model.