| 动态电源管理的随机切换模型与策略优化 |
| |
| 引用本文： | 江琦,奚宏生,殷保群. 动态电源管理的随机切换模型与策略优化[J]. 计算机辅助设计与图形学学报, 2006, 18(5): 680-686 |
| |
| 作者姓名： | 江琦 奚宏生 殷保群 |
| |
| 作者单位： | 中国科学技术大学自动化系,合肥,230027;中国科学技术大学自动化系,合肥,230027;中国科学技术大学自动化系,合肥,230027 |
| |
| 基金项目： | 中国科学院资助项目;安徽省自然科学基金 |
| |
| 摘 要： | 提出一种基于连续时间Markov决策过程的动态电源管理策略优化方法.通过建立动态电源管理系统的随机切换模型,将动态电源管理问题转化为带约束的策略优化问题,并给出一种基于矢量合成的策略梯度优化算法.随机切换模型对动态电源管理系统的描述精确,策略优化算法简便有效,既能离线计算,也适用于在线优化.仿真实验验证了该方法的有效性.
|
| 关 键 词： | 动态电源管理 Markov决策过程 随机切换模型 策略优化 梯度算法 |
| 收稿时间： | 2005-04-16 |
| 修稿时间： | 2005-12-19 |
Stochastic Switching Model and Policy Optimization for Dynamic Power Management |
| |
| Jiang Qi,Xi Hongsheng,Yin Baoqun. Stochastic Switching Model and Policy Optimization for Dynamic Power Management[J]. Journal of Computer-Aided Design & Computer Graphics, 2006, 18(5): 680-686 |
| |
| Authors: | Jiang Qi Xi Hongsheng Yin Baoqun |
| |
| Affiliation: | Department of Automation, University of Science and Technology of China, Hefei 230027 |
| |
| Abstract: | Based on continuous-time Markov decision processes, a power management policy optimization approach is proposed. First an event-driven stochastic switching model is introduced for power-managed systems. Under this model, the problem of dynamic power management is formulated as a constrained policy optimization problem. Then an efficient synthetic gradient-based policy optimization algorithm is presented. This algorithm can be employed to on-line optimization as well as off-line numerical computation.Finally, a simulation example is given to illustrate the effectiveness of the proposed approach. |
| |
| Keywords: | dynamic power management Markov decision processes stochastic switching model policy optimization gradient algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
