Quality-of-Service Optimization for Multiple Multimedia Tasks in Real-Time Embedded Systems

Nowadays, most embedded systems support different kinds of multimedia applications and real-time tasks. The computational requirements of multimedia applications are usually very demanding and embedded systems may not be powerful enough to support multiple multimedia applications. As a result, real-time tasks will miss their deadlines and thus get rejected. To solve this problem, we propose a Dynamic Workload Shaping (DWS) method by extending a Dynamic Buffering Technique (DBT) to multiple multimedia tasks and proposing two optimization methods. The original DBT scheduling method can only guarantee that the playout devices are always able to read out data items from the playout buffers, but does not guarantee any QoS. Two algorithms are proposed in this work to optimize and guarantee the quality of multimedia applications. We use several examples to illustrate how both algorithms can be applied to real systems. With MPEG-4 and H.264 applications, our experimental results show that the lower bound of 15 frames per second for the output device rates of the two multimedia applications can be guaranteed even if the processor frequency that can be allocated to them is very small. The processor frequency for running other real-time applications can be saved 10% to 15% if the multimedia applications run at their corresponding minimum processor frequencies that were computed by the guaranteeing QoS method.