Interoperable execution of escience applications on grids & clouds through open standards

The advent of cloud computing has offered scientific communities the ability to access computational resources that can satisfy their growing research needs starting to outgrow the size of traditional local resources as PCs and locally managed clusters and also of grid sites. Since grids and clouds are heterogeneous in nature and are based on different middlewares, interoperability between the service interfaces exposing the capabilities of these infrastructures is recognized as an important issue. This problem is usually handled by using the appropriate adaptors to interact with several middlewares thus allowing the applications to be executed on federated infrastructures. While aiming for federated resources access, there is an overhead for the application clients to continuously detect and adapt to every evolution of the target middlewares. In the presented work a complementary approach is followed to circumvent this problem by enabling interoperability between different execution services through the adoption of open and widely adopted standards.