A predictive dynamic power management technique for embedded mobile devices

It is becoming crucial to manage devices intelligently to reduce the power consumption of mobile embedded systems. Power-aware system management relies on techniques of collecting and analyzing information on the status of Input/Output (I/O) devices or processors while the system is running applications. However, the overhead of collecting information using software while the system is running is so huge that performance of the system may be severely degraded. Therefore, designing a Power Management Unit (PMU) that collects information and analyzes the information with some hardware support is very important. In this paper, we propose a novel PMU design that collects and analyzes access patterns to I/O devices while an application is being executed. We also propose a predictive power-aware management scheme which is carried out based on the collected information. Experiments with various applications have been conducted to show the effectiveness of our approach.