摘要
传统DVS算法在能量管理方面没有考虑实际系统性能的需求,这在一定意义上限制了其节能效果.针对这一问题,提出一种基于DVS技术的性能感知反馈调度算法.在反馈调度器中,分别采用DVS技术和模糊控制技术设计CPU电压调节模块和控制任务周期调节模块,实现对系统CPU速率和控制任务采样周期的动态调节.通过与基于固定采样周期的DVS反馈调度算法进行对比,结果表明该算法在保证系统控制性能的同时进一步降低了系统能耗.
Traditional DVS algorithms have inherent limitation on their capability in energy management because the system performance is not considered. A DVS-based performance-aware feedback scheduling algorithm is proposed to overcome this limitation. In the proposed feedback scheduler, DVS technology and fuzzy control technology are used respectively to design the CPU voltage adjustment module and control tasks periods adjustment module. CPU speed and control tasks sampling periods are dynamically regulated by this two-module scheduler. Simulation results show that the proposed algorithm is able to ensure the system control performance while further reduce the energy consumption of the system by comparing with the DVS feedback scheduling algorithm based on fixed sampling periods.
出处
《计算机系统应用》
2014年第2期166-172,共7页
Computer Systems & Applications
基金
陕西省自然科学基金(2013JM8026)
西北工业大学基础研究基金(2011JC0242)
关键词
性能感知
反馈调度
动态电压调节
模糊控制
嵌入式系统
performance-aware
feedback scheduling
Dynamic Voltage Scaling（DVS）
fuzzy control
embedded systems
