In recent years, Jungle Computing has emerged as a distributed computing paradigm based on simultaneous combination of various hierarchical and distributed computing environments which are composed by large number of heterogeneous resources. In such a computing environment, the resources and the underlying computation and communication infrastructures are highly-hierarchical and heterogeneous. This creates a lot of difficulty and complexity for finding the proper resources in a precise way in order to run a particular job on the system efficiently. This paper proposes Hybrid Adaptive Resource Discovery (HARD), a novel efficient and highly scalable resource-discovery approach which is built upon a virtual hierarchical overlay based on self-organization and self-adaptation of processing resources in the system, where the computing resources are organized into distributed hierarchies according to a proposed hierarchical multi-layered resource description model. The proposed approach supports distributed query processing within and across hierarchical layers by deploying various distributed resource discovery services and functionalities in the system which are implemented using different adapted algorithms and mechanisms in each level of hierarchy. The proposed approach addresses the requirements for resource discovery in Jungle Computing environments such as high-hierarchy, high-heterogeneity, high-scalability and dynamicity. Simulation results show significant scalability and efficiency of the proposed approach over highly heterogeneous, hierarchical and dynamic computing environments.
- Distributed operation systems
- Many-core systems
- Resource management
- Grid computing