控制理论与应用2024，Vol.41Issue(6)：1047-1055,9.DOI:10.7641/CTA.2023.20916
深度强化学习算法求解动态流水车间实时调度问题
Deep reinforcement learning algorithm for dynamic flow shop real-time scheduling problem
摘要
Abstract
This paper aims at the dynamic flow shop scheduling problem(DFSP),an adaptive deep reinforcement learning algorithm(ADRLA)is proposed to minimize the maximum completion time of DFSP.Firstly,the solving process of DFSP is described by the Markov decision process(MDP),so as to transform the DFSP into a sequential decision problem that can be solved by reinforcement learning.Then,according to the characteristics of DFSP scheduling model,the state representation vector with good state feature discrimination and generalization is designed,and five specific actions are proposed(i.e.reward value).Furthermore,the deep double Q network(DDQN)is used as the agent in ADRLA to make scheduling decisions.After training with the data set determined by a small number of small-scale DFSPs(i.e.the data of three basic elements on different problems),the agent can accurately describe the nonlinear relationship between the state representation vector and the Q-value vector(composed of the Q-value of each action)of different scale DFSPs,so as to carry out adaptive real-time scheduling for various scale DFSPs.Finally,simulation experiments on different test problems and comparison with the algorithm verify the effectiveness and real-time performance of the proposed ADRLA in solving DFSP.关键词
流水车间调度/新工件到达/深度强化学习/动态实时调度/智能调度Key words
flow shop scheduling/arrival of new jobs/deep reinforcement learning/dynamic real-time scheduling/intelligent scheduling引用本文复制引用
杨媛媛,胡蓉,钱斌,张长胜,金怀平..深度强化学习算法求解动态流水车间实时调度问题[J].控制理论与应用,2024,41(6):1047-1055,9.基金项目
国家自然科学基金项目(62173169,61963022),云南省基础研究重点项目(202201AS070030)资助.Supported by the National Natural Science Foundation of China(62173169,61963022)and the Basic Research Key Project of Yunnan Province Province(202201AS070030). （62173169,61963022）
