Slack-nibbling battery-aware task scheduling

Abstract

Dynamic voltage scaling (DVS) is an efficient approach to maximize the battery life of portable devices. A novel overall planning strategy (OPS II) balancing slack supply and demand for DVS is proposed. An OPS II-based slack-nibbling overall planning strategy (SNOPS) algorithm is also proposed, which iteratively nibbles slacks for appropriate tasks selected by an overall planning dynamic priority function to perform DVS until the slack is exhausted and an optimum voltage setting is obtained. For a high-load task set, SNOPS manages to recover battery overload while maintaining schedulability. For random variable-load task sets, SNOPS achieves a saving of 29.51% battery capacity on average, the suboptimal gap is 27.84% narrower than that of our previously proposed OPS-based algorithm, and 92.10% narrower than that of the algorithm proposed by Chowdhury et al. Results indicate that OPS II manages to save battery to various extents while maintaining schedulability, and demonstrates good load compatibility and close-to-optimal performance on average.