Dynamic parallel machine scheduling with random breakdowns using the learning agent
Dynamic parallel machine scheduling with random breakdowns using the learning agent
复制标题
使用学习代理进行随机故障的动态并行机调度
DOI：
10.1504/ijsoi.2016.10001001
复制
发表时间：
2016-11
期刊：
影响因子：
--
通讯作者：
Lei Wang
中科院分区：
文献类型：
--
作者：
Biao Yuan;Zhibin Jiang;Lei Wang
Agent技术以其灵活性、自治性、可扩展性等特点在制造过程中得到了广泛的应用。提出了一种基于学习代理的并行机动态调度方法。代理的职责是根据环境的当前状态，动态地将到达的作业分配给空闲机器，该代理基于Q-学习算法。一个涉及机器故障的状态动作表被构造来定义代理环境的状态。代理的行为采用最短处理时间（SPT）、最早交货期（EDD）和先到先得（FCFS）三种规则，代理采用e-贪婪策略选择行为。在仿真实验中，两个不同的目标，包括最大迟到和最小化的比例拖期作业，被用来验证学习代理的能力。结果表明，该智能体适用于复杂的并行机环境。
Agent technology has been widely applied in the manufacturing process due to its flexibility, autonomy, and scalability. In this paper, the learning agent is proposed to solve a dynamic parallel machine scheduling problem which considers random breakdowns. The duty of the agent, which is based on the Q-learning algorithm, is to dynamically assign arriving jobs to idle machines according to the current state of its environment. A state-action table involving machine breakdowns is constructed to define the state of the agent's environment. Three rules, including SPT (Shortest Processing Time), EDD (Earliest Due Date) and FCFS (First Come First Served), are used as actions of the agent, and the e-greedy policy is adopted by the agent to select an action. In the simulation experiment, two different objectives, including minimising the maximum lateness and minimising the percentage of tardy jobs, are utilised to validate the ability of the learning agent. The results demonstrate that the proposed agent is suitable for the complex parallel machine environment.