Skip to Main Content
In high performance computing field such as climate, biology, we often need to integrate resources across distributed, heterogeneous, and autonomous systems to enable e-scientists to solve complex scientific problems in collaborative way. However, current resource (service) collaboration methods still suffer from either low efficiency for automatically building a composition plan because of the involved ontology reasoning and manual processing, or lacking of flexibility for resource's sharing to support the execution of such composition plans. In this paper, we present a QSQL-based collaboration framework to support automatic service discovery, composition and execution. Our proposed method has the following two distinguished characteristics. First, for a given query, abstract composition plans can be automatically created basing on QSQL without much ontology reasoning. Secondly, concrete service instances can be dynamically bound to abstract service composition plans at runtime by considering multiple nonfunctional factors. Totally, our proposed method will not only facilitate e-scientists quickly create composition plans from a large scale of service repository; but also make resource's sharing more flexible.