Specific Versus Diverse Computing in Media Cloud

Abstract

Specific computing (SC) and diverse computing (DC), as two main visual computation manners, have been widely utilized in the media cloud. However, how to choose SC or DC in a practical scenario is still an open and challenging problem. Unfortunately, traditional fluid-based analysis method can not address this issue due to the uncertain relationship between the computing manner and service dynamics. In this work, we analytically study the characteristics of SC and DC by designing a so-called collapsing approximation (CA) method to precisely approximate the distribution of the service dynamics. On the qualitative end, we derive an exact expression for the dynamics of CA, thus enabling the cloud designer to choose different computing manners according to the application requests and analyze its impact regarding to the degrees of DC. On the technical end, we show that the evolution of the service dynamics process can be approximated by the unique solution to a collapsing model over a finite time period. The highlight of this paper lies in demonstrating that the optimal computing configuration should largely depend on SC, and a little on DC.