GENIUS: a generator of interactive user media sessions

The generation of realistic interactive synthetic streaming media workloads is of great importance for the effective evaluation of alternative media distribution techniques. This paper fills a gap left by previous studies and proposes a hierarchical model that captures key aspects of media user behavior and workloads, in particular, interactivity and heterogeneity. It also introduces GENIUS, a highly flexible and realistic streaming media workload generator that implements the proposed model and is parameterized with results from an extensive characterization of a rich set of real media workloads. Preliminary experiments show that our generator accurately captures workload aspects of key impact to system performance.