Real-time transcoding of MPEG videos in a distributed environment

As the market of mobile devices for video streaming is growing rapidly, it is necessary to convert a high bit rate MPEG stream into a low bit rate MPEG stream. However, it takes long time to transcode MPEG to another steaming media format due to the huge amount of computation in a traditional single computing environment. Furthermore, real-time MPEG transcoding also demands high computational power. Fortunately, the algorithms compliant to the MPEG standard can be parallelized. In this paper, we propose several scheduling algorithms for real-time transcoding of MPEG video that can be used in heterogeneous distributed computing environments. In the experiment, we will compare their performance through an experimental evaluation.