Multimedia Data Elevation under a Hierarchical Storage Model

Multimedia data storage is a critical issue in large scale applications. This paper proposes a frequency based multimedia data representation model which effectively guides data storage and elevation among the secondary and tertiary storage levels. Multimedia data are stored on the tertiary storage level and (based on certain popularity criteria) they are elevated on secondary level towards improving both the request servicing and the data’s accessibility. The proposed multimedia data elevation is a prefetching approach since it is performed “a priori” (not on demand) based on available information on users access patterns. Secondary storage placement is performed by the use of two distinct type placement policies, namely the “Constructive Placement” and the “Iterative Improvement” algorithms. A simulation model has been developed to evaluate the proposed hierarchical data model and the applied placement strategies. Experimentation results have shown that the this hierarchical approach under the iterative improvement placement outperforms earlier related multimedia data placement policies.