Resource Management Using Virtual Ontologies for Scientific Applications

Cloud computing has recently paid attention as a way to share the resources to provide scalable and on-demand services. Across various authorities, cloud resources should be configured to a virtual organization (VO) according to user's requirements. Ontology-based representation of cloud computing environment would be able to conceptualize common attributes among cloud resources and to represent semantic relations among them. However, mutual compatibility among different VOs is limited because a method applying ontology to cloud is in progress. We propose to introduce a resource virtualization method using virtual ontology. A new virtual ontology (VOn) is configured dynamically based on requirement of users, and the VOn is mapped to actual cloud resources. Our service uses a map/reduce model for rapid and efficient merging a number of ontology. The execution environment is orchestrated with selected resources mapped to the VOn, which is generated by ontology merge engine.