Partitioning the Program into different regions using dynamic and Static Approach with kernel-Assisted in Power management for Embedded System

Abstract

Today many embedded systems are driven by battery. The power consumption is becoming a critical problem for devices which are battery-powered. In this paper we presented a new approach for power management. We partitioned the Programs into different regions by Complier statically. And partitioning or merging regions dynamically according the performance statistic. The results showed that using dynamic and static approach together can save more energy than only using static method.

Coordinating System Software for Power Savings

“…And splitting or combining the code regions at run time leads to more power savings than using static method solely [15].…”

“…We have proposed a few power saving methodologies for almost all the phases of an application's life cycle [11,12,14,15,16]. In this paper, we integrate them into one system whose architecture is illustrated in Figure 1.…”

“…We import the methodology in [15,16] that splits and combines the code regions dynamically to our system. We use a modified compiler to scan the source code and find the desired regions.…”

An Energy-Efficient Strategy for Microcontrollers

“…They proposed that the most energy-efficient processor clock frequency is below the designed maximum frequency, and the relationship between the energy consumption and frequency presents a U-shaped curve. In addition, because the voltage transitions can require time on the order of tens of microseconds [32], Jiangwei et al [33], Pinheiro et al [34], and Kuehn et al [35] pointed out that the operation of processor frequency scaling can also introduce additional energy consumption because of the transition time overhead.…”

“…Our first assumption was that a higher processor frequency leads to more power consumption but a shorter execution time, so in the case of computationally intensive tasks, a higher processor clock frequency may not necessarily mean more energy consumption. In [32][33][34][35], it was pointed out that some widely used low-power technologies such as DVFS and power modes may have heavy overheads of transitions. We want to figure out a way to determine the application scenarios of different low-power technologies, so that microcontrollers can always run in the most energy-efficient way.…”