A semi-Markov decision process based dynamic power management for mobile devices

Abstract

Power management for mobile devices, such as smartphone and tablet, are more important than ever because the growth of battery density doesn't satisfy the increasing demand for user experience with various applications. However, existing approaches have more or less drawbacks: (1) focusing on certain sub-system and neglecting global optimization, (2) having a great burden on computation or data collection, (3) the risk of exposing user's privacy information. In this paper, we present a semi-Markov decision process (SMDP) based power management solution that balances user experience and power consumption. We choose GPS sampling rate and LCD brightness as control variables. This approach has less state number and needs less computation time. The simulation results show that the proposed solution can prolong usage time for about 53% and increase total experience by about 51% in comparison with the general fixed policy.