Unified energy aware mapping of multimedia applications on media cloud infrastructure

Media clouds provide an infrastructure for distributed processing and storage of multimedia applications. Each device in the media cloud is usually a mobile system consisting of several heterogeneous Processing Elements (PE). Energy efficiency has always been a challenge in this environment. In this paper, we propose a unified energy efficient algorithm for mapping multimedia applications on a media cloud infrastructure. The algorithm considers the distribution of tasks at two levels: among devices in the cloud and PEs of each device. The proposed algorithm heuristically finds the most energy efficient device for each task at the first stage. In the second stage, the least energy consuming PE among all available PEs is chosen for mapping. The efficiency of the proposed scheme has been evaluated by mapping H.264/AVC decoder on a media cloud. Simulation results indicate that by offloading application tasks on more power efficient PEs, the overall energy consumption for this application would be reduced by up to 12 times in a typical scenario in comparison to local processing. Meanwhile, the performance of the heuristic has been compared to the optimal solution.