高级动态电源管理在系统软件层的设计与实现

AN APPROACH TO SYSTEM-LEVEL ADVANCED DYNAMIC POWER MANAGEMENT

现在可移动嵌入式系统在飞速发展,而相应的电池技术发展速度却与之不符,这就使得电源管理成为了一个迫切需要解决的问题。动态电源管理(DPM)就是一种有效的系统级电源管理策略,它在恰当的时机选择性地切换设备状态,其目的是节省系统功耗以及系统响应延时。介绍了现有的几种DPM策略,如贪婪策略、超时策略、预判策略以及随机模型最优化策略等等,通过分析现有策略的优缺点,提出了一种系统级高级动态电源管理策略(ADPM),并在软件模拟环境中实现了ADPM策略和现有的其它几种DPM策略,并通过实验将几种策略进行比较,结果表明,ADPM在系统响应速度上要平均提高13%,在功耗节省上平均要提高16%,证明ADPM是一种有效的动态电源管理策略。

Nowadays, most battery supported portable embedded systems have developed rapidly, however, the development of battery technology is at a relatively slower pace, which makes power management become an important problem to be solved by the system designers. Dynamic power management（DPM） is an effective system-level power management policy which selectively switches device power state at right time in order to save power consumption within the system delay limitation. Several DPM policies such as Greedy,Time-out, Predictive and Stochastic Model are introduced. In addition, a kind of advanced dynamic power management （ADPM） policy is presented, and it is implemented along with many other DPM policies with software simulator. An experiment is made to compare the performance of these policies in terms of system delay and power consumption. The result shows that ADPM makes an average improvement of about 13% in system response and 16% in power saving, which indicates that ADPM is an effective power management policy.