Deep Reinforcement Learning Solves Job-shop Scheduling Problems

To solve the sparse reward problem of job-shop scheduling by deep reinforcement learning,a deep reinforcement learning framework considering sparse reward problem is proposed.The job shop scheduling problem is transformed into Markov decision process,and six state features are designed to improve the state feature representation by using two-way scheduling method,including four state features that distinguish the optimal action and two state features that are related to the learning goal.An extended variant of graph isomorphic network GIN++is used to encode disjunction graphs to improve the performance and generalization ability of the model.Through iterative greedy algorithm,random strategy is generated as the initial strategy,and the action with the maximum information gain is selected to expand it to optimize the exploration ability of Actor-Critic algorithm.Through validation of the trained policy model on multiple public test data sets and comparison with other advanced DRL methods and scheduling rules,the proposed method reduces the minimum average gap by 3.49%,5.31%and 4.16%,respectively,compared with the priority rule-based method,and 5.34%compared with the learning-based method.11.97%and 5.02%,effectively improving the accuracy of DRL to solve the approximate solution of JSSP minimum completion time.

Energy-Saving Distributed Flexible Job Shop Scheduling Optimization with Dual Resource Constraints Based on Integrated Q-Learning Multi-Objective Grey Wolf Optimizer

The distributed flexible job shop scheduling problem(DFJSP)has attracted great attention with the growth of the global manufacturing industry.General DFJSP research only considers machine constraints and ignores worker constraints.As one critical factor of production,effective utilization of worker resources can increase productivity.Meanwhile,energy consumption is a growing concern due to the increasingly serious environmental issues.Therefore,the distributed flexible job shop scheduling problem with dual resource constraints(DFJSP-DRC)for minimizing makespan and total energy consumption is studied in this paper.To solve the problem,we present a multi-objective mathematical model for DFJSP-DRC and propose a Q-learning-based multi-objective grey wolf optimizer(Q-MOGWO).In Q-MOGWO,high-quality initial solutions are generated by a hybrid initialization strategy,and an improved active decoding strategy is designed to obtain the scheduling schemes.To further enhance the local search capability and expand the solution space,two wolf predation strategies and three critical factory neighborhood structures based on Q-learning are proposed.These strategies and structures enable Q-MOGWO to explore the solution space more efficiently and thus find better Pareto solutions.The effectiveness of Q-MOGWO in addressing DFJSP-DRC is verified through comparison with four algorithms using 45 instances.The results reveal that Q-MOGWO outperforms comparison algorithms in terms of solution quality.

Modified bottleneck-based heuristic for large-scale job-shop scheduling problems with a single bottleneck

A modified bottleneck-based （MB） heuristic for large-scale job-shop scheduling problems with a welldefined bottleneck is suggested, which is simpler but more tailored than the shifting bottleneck （SB） procedure. In this algorithm, the bottleneck is first scheduled optimally while the non-bottleneck machines are subordinated around the solutions of the bottleneck schedule by some effective dispatching rules. Computational results indicate that the MB heuristic can achieve a better tradeoff between solution quality and computational time compared to SB procedure for medium-size problems. Furthermore, it can obtain a good solution in a short time for large-scale jobshop scheduling problems.

A Modi ed Iterated Greedy Algorithm for Flexible Job Shop Scheduling Problem

The flexible job shop scheduling problem(FJSP) is considered as an important problem in the modern manufacturing system. It is known to be an NP-hard problem. Most of the algorithms used in solving FJSP problem are categorized as metaheuristic methods. Some of these methods normally consume more CPU time and some other methods are more complicated which make them di cult to code and not easy to reproduce. This paper proposes a modified iterated greedy(IG) algorithm to deal with FJSP problem in order to provide a simpler metaheuristic, which is easier to code and to reproduce than some other much more complex methods. This is done by separating the classical IG into two phases. Each phase is used to solve a sub-problem of the FJSP: sequencing and routing sub-problems. A set of dispatching rules are employed in the proposed algorithm for the sequencing and machine selection in the construction phase of the solution. To evaluate the performance of proposed algorithm, some experiments including some famous FJSP benchmarks have been conducted. By compared with other algorithms, the experimental results show that the presented algorithm is competitive and able to find global optimum for most instances. The simplicity of the proposed IG provides an e ective method that is also easy to apply and consumes less CPU time in solving the FJSP problem.

Clonal Selection Based Memetic Algorithm for Job Shop Scheduling Problems

A clonal selection based memetic algorithm is proposed for solving job shop scheduling problems in this paper. In the proposed algorithm, the clonal selection and the local search mechanism are designed to enhance exploration and exploitation. In the clonal selection mechanism, clonal selection, hypermutation and receptor edit theories are presented to construct an evolutionary searching mechanism which is used for exploration. In the local search mechanism, a simulated annealing local search algorithm based on Nowicki and Smutnicki＇s neighborhood is presented to exploit local optima. The proposed algorithm is examined using some well-known benchmark problems. Numerical results validate the effectiveness of the proposed algorithm.

Solving Job-Shop Scheduling Problem Based on Improved Adaptive Particle Swarm Optimization Algorithm

An improved adaptive particle swarm optimization(IAPSO)algorithm is presented for solving the minimum makespan problem of job shop scheduling problem(JSP).Inspired by hormone modulation mechanism,an adaptive hormonal factor(HF),composed of an adaptive local hormonal factor(H l)and an adaptive global hormonal factor(H g),is devised to strengthen the information connection between particles.Using HF,each particle of the swarm can adjust its position self-adaptively to avoid premature phenomena and reach better solution.The computational results validate the effectiveness and stability of the proposed IAPSO,which can not only find optimal or close-to-optimal solutions but also obtain both better and more stability results than the existing particle swarm optimization(PSO)algorithms.

Solving flexible job shop scheduling problem by a multi-swarm collaborative genetic algorithm

The flexible job shop scheduling problem(FJSP),which is NP-hard,widely exists in many manufacturing industries.It is very hard to be solved.A multi-swarm collaborative genetic algorithm(MSCGA)based on the collaborative optimization algorithm is proposed for the FJSP.Multi-population structure is used to independently evolve two sub-problems of the FJSP in the MSCGA.Good operators are adopted and designed to ensure this algorithm to achieve a good performance.Some famous FJSP benchmarks are chosen to evaluate the effectiveness of the MSCGA.The adaptability and superiority of the proposed method are demonstrated by comparing with other reported algorithms.

Applying Job Shop Scheduling to SMEs Manufacturing Platform to Revitalize B2B Relationship

A small and medium enterprises(SMEs)manufacturing platform aims to perform as a significant revenue to SMEs and vendors by providing scheduling and monitoring capabilities.The optimal job shop scheduling is generated by utilizing the scheduling system of the platform,and a minimum production time,i.e.,makespan decides whether the scheduling is optimal or not.This scheduling result allows manufacturers to achieve high productivity,energy savings,and customer satisfaction.Manufacturing in Industry 4.0 requires dynamic,uncertain,complex production environments,and customer-centered services.This paper proposes a novel method for solving the difficulties of the SMEs manufacturing by applying and implementing the job shop scheduling system on a SMEs manufacturing platform.The primary purpose of the SMEs manufacturing platform is to improve the B2B relationship between manufacturing companies and vendors.The platform also serves qualified and satisfactory production opportunities for buyers and producers by meeting two key factors:early delivery date and fulfillment of processing as many orders as possible.The genetic algorithm(GA)-based scheduling method results indicated that the proposed platform enables SME manufacturers to obtain optimized schedules by solving the job shop scheduling problem(JSSP)by comparing with the real-world data from a textile weaving factory in South Korea.The proposed platform will provide producers with an optimal production schedule,introduce new producers to buyers,and eventually foster relationships and mutual economic interests.

APPLYING PARTICLE SWARM OPTIMIZATION TO JOB-SHOPSCHEDULING PROBLEM

A new heuristic algorithm is proposed for the problem of finding the minimummakespan in the job-shop scheduling problem. The new algorithm is based on the principles ofparticle swarm optimization (PSO). PSO employs a collaborative population-based search, which isinspired by the social behavior of bird flocking. It combines local search (by self experience) andglobal search (by neighboring experience), possessing high search efficiency. Simulated annealing(SA) employs certain probability to avoid becoming trapped in a local optimum and the search processcan be controlled by the cooling schedule. By reasonably combining these two different searchalgorithms, a general, fast and easily implemented hybrid optimization algorithm, named HPSO, isdeveloped. The effectiveness and efficiency of the proposed PSO-based algorithm are demonstrated byapplying it to some benchmark job-shop scheduling problems and comparing results with otheralgorithms in literature. Comparing results indicate that PSO-based algorithm is a viable andeffective approach for the job-shop scheduling problem.

Job shop scheduling problem based on DNA computing

To solve job shop scheduling problem, a new approach-DNA computing is used in solving job shop scheduling problem. The approach using DNA computing to solve job shop scheduling is divided into three stands. Finally, optimum solutions are obtained by sequencing A small job shop scheduling problem is solved in DNA computing, and the ＂operations＂ of the computation were performed with standard protocols, as ligation, synthesis, electrophoresis etc. This work represents further evidence for the ability of DNA computing to solve NP-complete search problems.

A Grafted Genetic Algorithm for the Job-Shop Scheduling Problem

The standard genetic algorithm has limitations of a low convergence rate and premature convergence in solving the job-shop scheduling problem.To overcome these limitations,this paper presents a new improved hybrid genetic algorithm on the basis of the idea of graft in botany.Through the introduction of a grafted population and crossover probability matrix,this algorithm accelerates the convergence rate greatly and also increases the ability to fight premature convergence.Finally,the approach is tested on a set of standard instances taken from the literature and compared with other approaches.The computation results validate the effectiveness of the proposed algorithm.

基于遗传算法的JobShop调度问题研究

在多平行工作站环境下,为使限定资源分配下的车间调度问题(Job Shop problem,JSP)具有最小总延迟时间;同时又可设定各订单具有不同的开工日(release date)及到期日,提出以可开工时间与结束时间为基础的分解解法,并在遗传算法的基础上构造混合遗传算法(hybrid genetic algorithm,HGA)来实现目标设定。实验结果表明,HGA在问题求解质量与Lingo解的最佳解差异在15%以内,并具备较基本型遗传算法更佳的稳定性。结果显示该算法可帮助管理人员实现智能资源配置与订单调度。

解决Job Shop调度问题的模拟退火算法改进

模拟退火算法是较常用和较理想的解决车间作业调度问题的方法,但由于算法本身的限制和JSP问题的特殊性,其效能难以很好地发挥。该文提出了2种针对JSP问题的改进模拟退火算法:回火退火算法和快速模拟退火算法,前者可以提高最终解质量,后者可以提高算法的运行速度;并以Matlab为工具进行了仿真实验,获得了较好效果。

解决JOB SHOP问题的粒子群优化算法

设计了2种解决Job shop问题的粒子群算法,即实数编码的粒子群调度算法和工序编码的粒子群调度算法。工序编码的粒子群调度算法更符合Job shop问题的特点,优化性能相对高。但粒子群调度算法容易陷入局部最优。为了提高优化性能,将粒子群算法和模拟退火算法结合,得到了粒子群-模拟退火混合调度算法。仿真结果表明了算法的有效性。

遗传算法求解柔性job shop调度问题

在分析柔性jobshop调度问题特点的基础上,提出一种新的求解该问题的遗传算法,即利用编码方法表示各工序的优先调度顺序及工序的加工机器,由此产生可行的调度方案,使得问题的约束条件在染色体中得以体现.所设计的遗传算子不仅能避免非法调度解的出现,保证后代的多样性,而且可使算法具有记忆功能.仿真结果证明了该算法的有效性.

一种求解Job-shop调度问题的遗传局部搜索算法

利用遗传局部搜索算法求解了作业车间调度问题,遗传算法中的染色体编码采用基于工序的编码,并用插入式贪婪解码机制将染色体解码至主动调度。为了克服传统遗传算法易于早熟收敛的缺点,设计了一种改进的优先操作交叉IPOX操作和子代产生模式的遗传算法。对于遗传算法每个染色体个体,使用基于N6邻域结构的局部搜索进一步使它们得到改善。利用所提出的混合遗传算法求解基准问题,验证了算法的有效性。

免疫进化算法求解静态Job shop调度

基于克隆选择原理与细胞超变异思想构造了一种免疫进化算法CHIEA(Clonal selection and hyper mutations based immune evolution algorithm)求解静态JSP问题(Job shop scheduling problem)。随机混排变异算子的构造和抗体连续累积变异的实施丰富了细胞超变异的内容,基于优先列表编码方式的采用和免疫进化算子的构造提高了搜索效率,加速了算法收敛并提高了解的质量。通过与COELLO的AIS(Artificial immune system)算法的全面比较得出,CHIEA求解不同类型中小规模的静态JSP问题时具有更好的优化性能。

基于模糊规划的处理时间不确定条件下的Job shop问题

研究了处理时间不确定条件下的 Job shop生产调度问题 ,建立了基于模糊规划理论的不确定 Job shop调度模型。在采用两种模糊运算的基础上 ,结合模糊优化和遗传算法给出了一个解决非线性模糊优化问题的可行算法 ,通过仿真数据说明了所建模型及算法的有效性 。

Job-shop调度问题的瞬态混沌神经网络解法

采用具有瞬态混沌特性的神经网络 (TCNN)解 Job- shop调度问题。利用神经元的自抑制反馈产生混沌动态 ,其随机搜索能力有效地避免了传统 Hopfield神经网络 (HNN)极易陷入局部极小的缺陷 ;同时利用一时变参数控制混沌行为 ,使网络在经过一个短暂的倍周期倒分岔后逐渐趋于一般的神经网络 ,从而收敛到一个最优或近似最优的稳定平衡点。仿真结果表明 ,该网络解 Job- shop调度问题比 HNN具有更强的全局搜索能力和寻优能力 ,并具有更高的搜索效率。

应用改进微粒群算法求解Job-shop调度问题

针对微粒群算法在求解实际问题过程中会出现早熟的现象,提出一种改进的微粒群算法。该算法利用记忆库来动态调整惯性权重值,增快了算法的收敛速度。同时结合进化、灾变机制避免了算法陷入局部极值的问题。在列出改进算法的具体步骤基础上,通过实际的车间调度仿真实例证明了算法的有效性,可以得到比启发式、遗传算法更佳的调度效果。