To minimize battery consumption for portable devices, the prescheduling policy of battery-aware scheduling was im- proved by optimizing slack distribution. A battery-aware com- pound task scheduling (BACTS) algorithm considering various aspects including task deadline, current and execution time was proposed and evaluated with the previously prevailing earliest deadline first (EDF) algorithm. The results indicate the proposed BACTS algorithm manages to figure out a feasible schedule (if available) in battery-aware task scheduling even for disorganized connected task graphs beyond the solving ability of EDF. Its schedule achieves better performance with lower charge consump- tion after prescheduling, and also lower or equal optimum charge consumption after voltage scaling.
展开▼