首页 | 本学科首页   官方微博 | 高级检索  
     

嵌入式系统动态电源管理预测算法研究
引用本文:钟伟军,刘明业,彭刚. 嵌入式系统动态电源管理预测算法研究[J]. 微电子学与计算机, 2005, 22(11): 56-58,62
作者姓名:钟伟军  刘明业  彭刚
作者单位:1. 北京理工大学信息科学技术学院,北京,100081
2. 北京理工大学信息科学技术学院,北京,100081;厦门大学计算机与信息工程学院,福建,厦门,361005
摘    要:针对目前在嵌入式系统中动态电源管理普遍采用超时算法节能效率低的缺点,采用预测的方法进行动态电源管理.提出一个动态电源管理预测算法,该算法通过利用设备空闲状态的历史信息对未来的空闲时间进行预测,预测结果作为动态电源管理的依据.实验结果说明该算法对工作状态平稳的系统空闲预测效果比较理想,适用于动态电源管理.

关 键 词:动态电源管理  空闲预测  超时算法
文章编号:1000-7180(2005)11-056-03
收稿时间:2005-03-03
修稿时间:2005-03-03

Research on Predictive Algorithm of Dynamic Power Management in Embedded System
ZHONG Wei-jun,LIU Ming-ye,PENG Gang. Research on Predictive Algorithm of Dynamic Power Management in Embedded System[J]. Microelectronics & Computer, 2005, 22(11): 56-58,62
Authors:ZHONG Wei-jun  LIU Ming-ye  PENG Gang
Affiliation:1 School of Information Science and Technology,Beijing Institute of Technology, Beijing 100081 ;2 School of Computer and Information Engineering, Xiamen University, Xiamen 361005 China
Abstract:It is very low efficiency for saving energy that time-out algorithm is adopted as a policy of dynamic power management in embedded system. In order to improve efficiency, predicted method is introduced into technique to manage power dynamically. An algorithm is proposed to predict next idle period using previous information of idle period. The decision-making of dynamic power management is based on the predictive result of future idle period. The experimental result shows that the algorithm can predict idle period preferably in system with smooth workload and fits as policy of dynamic power management.
Keywords:Dynamic power management   Prediction of idle period   Time-out algorithm
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号