A Unified Management Model for Data Intensive Storage Clouds

Cloud storage has recently appeared as a promising solution to handle the immense volume of data produced in nowadays' rich and ubiquitous digital environment. Existing approaches, however, do not fully address certain significant issues, such as Service Level Agreements, which tend to be rudimentary, and management of cloud systems, which often lacks sophistication. In this paper, we propose the definition and development of management models that systematically describe the resources, services, usage, and requirements in the context of a cloud storage environment. Furthermore, we introduce content oriented SLA Schemas, which are adapted according to the content term involved in each SLA. Combining all this often heterogeneous information in a smart, structured, and uniform manner can provide significant added value, allowing correlations, links and extraction of useful inferences. We thus propose to incorporate these models in a rich Unified Management Model, which will contribute to optimum decision making, data movement, as well as better resource allocation and energy management, also leading to enhanced Quality of Service. The research presented in this paper is work in progress carried out in the context of the VISION Cloud project.