Towards Agents and Ontology for Cloud Service Discovery

Abstract

Cloud computing has attracted great interest from both academic and industrial communities. However, only a few efforts have been devoted to building tools for supporting Cloud service discovery. In this paper, we present a four-stage, agent-based Cloud service discovery protocol. Utilizing an ontology description, in which each resource is described semantically and relatively to other resources, we develop a multi-agent system that cooperates efficiently by introducing a flexible ontology-based matching. To increase the utility and success rate of matching consumers' requests to resources, we use a database to store and keep track of historical data for making intelligent recommendation based on attribute value prediction. Empirical results show that when broker agents in our system use a Cloud ontology and a connection procedure with a recommendation stage achieved better performance in finding the appropriate Cloud services than when broker agents 1) use only the connection procedure but not the Cloud ontology and 2) do not use both the connection procedure and the Cloud ontology.