| 基于聚类状态隶属度的动态调度Q-学习 |
| |
| 引用本文： | 王国磊,钟诗胜,林琳. 基于聚类状态隶属度的动态调度Q-学习[J]. 高技术通讯, 2009, 19(4). DOI: 10.3772/j.issn.1002-0470.2009.04.018 |
| |
| 作者姓名： | 王国磊 钟诗胜 林琳 |
| |
| 作者单位： | 哈尔滨工业大学机电工程学院,哈尔滨,150001 |
| |
| 基金项目： | 国家自然科学基金，国家高技术研究发展计划(863计划) |
| |
| 摘 要： | 提出了一种利用Q-学习解决动态单机调度环境下的自适应调度规则选择的方法.该方法针对动态调度环境中系统状态空间大,Q-学习不易收敛的特点,首先提取系统状态特征,对系统状态进行合理聚类,有效地降低系统状态空间维数,然后在学习过程中令设备Agent根据瞬时状态向量对各聚类状态的隶属度做出综合判断,选择合适规则,并在每次迭代后根据隶属度将动作奖惩分配给各聚类状态的动作值函数.仿真结果表明,所提Q-学习算法较之传统Q-学习具有更快的收敛速度,提高了设备Agent的动态调度规则选择能力.
|
| 关 键 词： | 动态调度 Q-学习 调度规则选择 状态聚类 隶属度 |
Clustering state membership-based Q-learning for dynamic scheduling |
| |
| Wang Guolei,Zhong Shisheng,Lin Lin. Clustering state membership-based Q-learning for dynamic scheduling[J]. High Technology Letters, 2009, 19(4). DOI: 10.3772/j.issn.1002-0470.2009.04.018 |
| |
| Authors: | Wang Guolei Zhong Shisheng Lin Lin |
| |
| Affiliation: | Wang Guolei Zhong Shisheng Lin Lin (School of Mechanical Engineering,Harbin Institute of Technology,Harbin 150001) |
| |
| Abstract: | Q-learning was applied to resolution of the adaptive dispatching rule selection problem under dynamic single-machine scheduling environment.Considering that Q-learning is hard to converge due to the large scale of the system state space during dynamic scheduling,the method extracts several state features of the system firstly,so that the dimension of the system state space can be reduced through the fuzzy clustering method .Then the machine agent can choose proper rules based on the transient system state m... |
| |
| Keywords: | dynamic scheduling Q-learning dispatching rule selection state clustering membership |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
