Digital twin-based job shop anomaly detection and dynamic scheduling

Scheduling scheme is one of the critical factors affecting the production efficiency. In the actual production, anomalies will lead to scheduling deviation and influence scheme execution, which makes the traditional job shop scheduling methods are not sufficient to meet the needs of real-time and accuracy. By introducing digital twin (DT), further convergence between physical and virtual space can be achieved, which enormously reinforces real-time performance of job shop scheduling. For flexible job shop, an anomaly detection and dynamic scheduling framework based on DT is proposed in this paper. Previously, a multi-level production process monitoring model is proposed to detect anomaly. Then, a real-time optimization strategy of scheduling scheme based on rolling window mechanism is explored to enforce dynamic scheduling optimization. Finally, the improved grey wolf optimization algorithm is introduced to solve the scheduling problem. Under this framework, it is possible to monitor the deviation between the actual processing state and the planned processing state in real time and effectively reduce the deviation. An equipment manufacturing job shop is taken as a case study to illustrate the effectiveness and advantages of the proposed framework.     

混合粒子群算法求解多目标柔性作业车间调度问题

柔性作业车间调度问题是生产管理领域和组合优化领域的重要分支.本文提出一种基于Pareto支配的混合粒子群优化算法求解多目标柔性作业车间调度问题.首先采用基于工序排序和机器分配的粒子表达方式,并直接在离散域进行位置更新.其次,提出基于BaldWinian学习策略和模拟退火技术相结合的多目标局部搜索策略,以平衡算法的全局探索能力和局部开发能力.然后引入Pareto支配的概念来比较粒子的优劣性,并采用外部档案保存进化过程中的非支配解.最后用于求解该类问题的经典算例,并与已有算法进行比较,所提算法在收敛性和分布均匀性方面均具有明显优势.     

Bi-level dynamic scheduling architecture based on service unit digital twin agents

Pure reactive scheduling is one of the core technologies to solve the complex dynamic disturbance factors in real-time. The emergence of CPS, digital twin, cloud computing, big data and other new technologies based on the industrial Internet enables information acquisition and pure reactive scheduling more practical to some extent. However, how to build a new architecture to solve the problems which traditional dynamic scheduling methods cannot solve becomes a new research challenge. Therefore, this paper designs a new bi-level distributed dynamic workshop scheduling architecture, which is based on the workshop digital twin scheduling agent and multiple service unit digital twin scheduling agents.Within this architecture, scheduling a physical workshop is decomposed to the whole workshop scheduling in the first level and its service unit scheduling in the second level. On the first level, the whole workshop scheduling is executed by its virtual workshop coordination (scheduling) agent embedded with the workshop digital twin consisting of multi-service unit digital twins. On the second level, each service unit scheduling coordinated by the first level scheduling is executed in a distributed way by the corresponding service unit scheduling agent associated with its service unit digital twin. The benefits of the new architecture include (1) if a dynamic scheduling only requires a single service unit scheduling, it will then be performed in the corresponding service unit scheduling without involving other service units, which will make the scheduling locally, simply and robustly. (2) when a dynamic scheduling requires changes in multiple service units in a coordinated way, the first level scheduling will be executed and then coordinate the second level service unit scheduling accordingly. This divide-and-then-conquer strategy will make the scheduling easier and practical.The proposed architecture has been tested to illustrate its feasibility and practicality.     

Filtered-beam-search-based algorithm for dynamic rescheduling in FMS

In the practical production process of a flexible manufacturing system (FMS), unexpected disturbances such as rush orders arrival and machine breakdown may inevitably render the existing schedule infeasible. This makes dynamic rescheduling necessary to respond to the disturbances and to improve the efficiency of the disturbed FMS. Compared with the static scheduling, the dynamic rescheduling relies on more effective and robust search approaches for its critical requirement of real-time optimal response. In this paper, a filtered-beam-search (FBS) -based heuristic algorithm is proposed to solve the dynamic rescheduling problem in a large and complicated job shop FMS environment with realistic disturbances. To enhance its performance, the proposed algorithm makes improvement in the local/global evaluation functions and the generation procedure of branches. With respect to a due date-based objective (weighted quadratic tardiness), computational experiments are studied to evaluate the performance of the proposed algorithm in comparison with those of other popular methods. The results show that the proposed FBS-based algorithm performs very well for dynamic rescheduling in terms of computational efficiency and solution quality.     

作业车间动态调度建模与仿真研究

针对作业车间动态调度问题进行了分析和建模,应用多微粒群协同优化理论,提出了一种制造业作业车间动态调度优化算法,通过基于Matlab的模拟与仿真,验证了本算法的有效性和高效性.     

含有运输小车的柔性作业车间调度研究

在实际的柔性作业车间调度中,不但工件需要加工时间,而且工件在各个机器之间利用AGV(自动导引小车)转移也需要占用一定的时间,因此对柔性作业车间调度中考虑AGV运输时间的研究更具有实际意义。针对此问题,本文建立含有AGV的柔性作业车间调度的数学模型,针对问题自身特点对遗传算法进行改进,引入局部搜索策略加强局部寻优能力,将模拟退火算法作为局部搜索策略加入全局搜索中,增强了算法的收敛性能。通过在仿真实验平台上的实验数据结果可以看出,本算法有比较好的效果。     

A simulated annealing algorithm for multi-agent systems: a job-shop scheduling application

In this paper, a parallel implementation of the modular simulated annealing algorithm for classical job-shop scheduling is presented. The implementation is for a multi agent system running on the distributed resource machine, which is a novel, scalable, distributed virtual machine based on Java technology. The problems tackled are well known, difficult benchmarks, widely used to measure the efficiency of metaheuristics with respect to both the quality of the solutions and the central processing unit time. The empirical results obtained show that the method proposed is successful in comparison with a sequential version of modular simulated annealing algorithm and other methods described in the literature.     

资源动态组织支持的网格依赖任务重调度机制

针对网格依赖任务重调度所面临的效率低与触发频繁的问题,提出资源动态组织支持的网格依赖任务调度机制.该机制以资源的动态组织为核心,基于资源动态性度量结果对资源进行性能聚类分析,并过滤性能相似资源中的强动态性资源,以在减少资源数量的同时提高重调度备选资源的稳定性.实验表明基于该机制的重调度算法保持了静态调度策略在动态网格环境下相对于动态调度策略的性能优势,从而验证了该机制解决网格依赖任务重调度所面临问题的有效性.     

Grid harvest service: A performance system of grid computing

Conventional performance evaluation mechanisms focus on dedicated systems. Grid computing infrastructure, on the other hand, is a shared collaborative environment constructed on virtual organizations. Each organization has its own resource management policy and usage pattern. The non-dedicated characteristic of Grid computing prevents the leverage of conventional performance evaluation systems. In this study, we introduce the grid harvest service (GHS) performance evaluation and task scheduling system for solving large-scale applications in a shared environment. GHS is based on a novel performance prediction model and a set of task scheduling algorithms. GHS supports three classes of task scheduling, single task, parallel processing and meta-task. Experimental results show that GHS provides a satisfactory solution for performance prediction and task scheduling of large applications and has a real potential.     

基于迁移技术的云资源动态调度策略研究

现有云资源管理平台存在着瞬时资源利用率峰值易引发迁移、动态负载效果不佳等问题。依据云资源动态调度模型,提出了有效的基于迁移技术的虚拟机动态调度算法。算法将物理节点负载与虚拟机迁移损耗评估、多次触发控制、目标节点定位三者有机结合,实现云计算数据中心高效的动态负载均衡。实验结果表明,该算法优于CloudSim的DVFS调度策略,在保证应用服务水平的同时能减少虚拟机迁移次数和物理机启用数量。     

面向多目标的云计算资源调度算法

在传统的虚拟机资源调度中,仅仅考虑当前负载,对虚拟机历史数据没有充分考虑,在处理云计算资源调度的时候出现负载失衡的状况,为了解决上述问题,本文提出了基于启发式遗传算法的资源调度算法,满足多目标规划的情况下实现云计算资源的调度.算法在为用户提供服务的同时充分考虑虚拟机的各种开销和因素,使提供云计算资源的服务器达到负载均衡.对目前的负载情况和历史数据进行分析,经过搜索和计算,计算得到同时满足负载变化数据约束和最小动态迁移开销的最好的云计算资源调度方案.最后,通过仿真实验,对算法进行验证,通过引入负载变化率和平均负载距离二个性能参数来比较和衡量虚拟机负载.实验数据证明,所提出的算法具有很好的全局收敛性和资源利用率,有效解决在资源调度中出现负载失衡和较大动态迁移开销的问题,因此,算法是可行和有效的.     

Multi-objective scheduling of dynamic job shop using variable neighborhood search

Dynamic job shop scheduling that considers random job arrivals and machine breakdowns is studied in this paper. Considering an event driven policy rescheduling, is triggered in response to dynamic events by variable neighborhood search (VNS). A trained artificial neural network (ANN) updates parameters of VNS at any rescheduling point. Also, a multi-objective performance measure is applied as objective function that consists of makespan and tardiness. The proposed method is compared with some common dispatching rules that have widely used in the literature for dynamic job shop scheduling problem. Results illustrate the high effectiveness and efficiency of the proposed method in a variety of shop floor conditions.     

Design of digital twin applications in automated storage yard scheduling

A digital twin-enabled automated storage yard scheduling framework for uncertain port dispatching is proposed in this paper. Digital twin technology is employed to establish the virtual yet realistic storage yard and the connection between them. In the proposed framework, disturbed scenarios during practical operation are monitored, and real-time data is visualized in the virtual space to adapt to the time-varying environment. The proposed framework focuses on the optimization of three main resources, viz. storage area, automated stacking cranes (ASCs), and automated guided vehicles (AGVs). In addition, three key technologies, the Internet of Things (IoT), virtual reality, and digital thread, are adopted to develop the proposed scheduling system. A case study of ASC rescheduling due to dynamic arrival is used to demonstrate the effectiveness of the proposed framework and the significance of obtaining uncertainties in port optimization. Sensitivity analysis is conducted to define the appropriate configuration required to handle all tasks. The results show that digital twin applications in automated storage yard scheduling help operators make optimization decisions.     

The role of algorithm and result comprehensibility of automated scheduling on complacency

Several studies have stressed that even expert operators who are aware of a machine's limits could adopt its proposals without questioning them (i.e., the complacency phenomenon). In production scheduling for manufacturing, this is a significant problem, as it is often suggested that the machine be allowed to build the production schedule, confining the human role to that of rescheduling. This article evaluates the characteristics of scheduling algorithms on human rescheduling performance, the quality of which was related to complacency. It is suggested that scheduling algorithms be characterized as having result comprehensibility (the result respects the scheduler's expectations in terms of the discourse rules of the information display) or algorithm comprehensibility (the complexity of the algorithm hides some important constraints). The findings stress, on the one hand, that result comprehensibility is necessary to achieve good production performance and to limit complacency. On the other hand, algorithm comprehensibility leads to poor performance due to the very high cost of understanding the algorithm. © 2008 Wiley Periodicals, Inc.     

Xen虚拟机的虚拟CPU松弛协同调度方法

目前,Xen虚拟机调度算法均采用独立调度虚拟CPU的方式,而没有考虑虚拟机各虚拟CPU之间的协同调度关系,这会使虚拟机各个虚拟CPU之间产生很大的时钟中断数量偏差等问题,从而导致系统不稳定.为了提高系统的稳定性,基于Credit算法提出了一种比RCS(relaxed co-scheduling)算法更松弛的协同调度算法MRCS(more relaxed co-scheduling).该算法采用非抢占式协同调整方法将各个虚拟CPU相对运行的时间间隔控制在同步时间检测的上限门限值Tmax之内,同时利用同步队列中虚拟CPU优化选择调度方法和Credit算法的虚拟CPU动态迁移方法,能够更加及时地协同处理虚拟CPU,并且保证了各个物理CPU的负载均衡,有效地减少客户操作系统与VMM的环境切换次数,降低了系统开销.实验结果证明该方法不但保证了系统的稳定性,而且使系统性能得到一定程度的提升.虚拟机调度算法不仅影响虚拟机的性能,更会影响虚拟机的稳定性,致力于虚拟机调度算法的研究是一项非常有意义的工作.     

云计算中基于共享机制和群体智能优化算法的任务调度方案

为了提高云计算中虚拟机(VM)的利用率并降低任务的完成时间,提出了一种融合共享机制的混合群智能优化算法,实现云任务的动态调度。首先,将虚拟机调度编码为蜜蜂、蚂蚁和遗传个体。然后,利用人工蜂群算法(ABC)、蚁群算法(ACO)和遗传算法(GA)分别在各自邻域内寻找最优解。最后,通过一个共享机制使3种算法定期交流各自搜索到的解,并将获得的最佳解作为当前最优解进行下一次迭代过程,以此来加速算法收敛并提高收敛精度。通过CloudSim进行了一个云任务调度的仿真实验,结果表明提出的混合算法能够合理有效地调度任务,在任务完成时间和稳定性方面具有优越的性能。     

基于二次指数平滑预测的虚拟机调度方法研究*

针对数据中心的高能耗问题,提出了一种基于负载感知和预测的虚拟机调度方法,采用二次指数平滑法预测物理主机资源负载情况,利用MMT和MM相结合的策略选择待迁虚拟机,使用资源最佳适配策略（BRF）选择目标物理主机。该调度方法的预测模型能提高迁移触发准确率,随着调度轮数的增加,对资源需求互补的虚拟机会被整合到相同物理主机上,从而减少迁移次数;最后,通过CloudSim仿真平台与FT_MMT、CDLC、AR_MMT调度策略进行了对比,结果表明该调度方法在能耗节约、迁移次数方面均有提升。     

基于负载预测的虚拟机动态调度算法研究与实现

在云计算系统中为了实现负载均衡和资源的高效利用,需要在虚拟机粒度上对云计算系统进行调度,通过热迁移技术将虚拟机从高负载物理节点迁移到低负载物理节点。把负载预测技术和虚拟机动态调度技术相结合,提出了LFS算法,通过虚拟机历史负载数据对虚拟机未来的负载变化情况进行预测,然后根据预测结果对虚拟机进行调度,能够有效地避免云计算系统中高负载物理节点出现,实现负载均衡,提高资源使用率。     

基于模糊物元模型的高维多目标FJSP研究*

为解决高维多目标柔性作业车间调度问题,提出了一种基于模糊物元模型与粒子群算法的模糊粒子群算法（Fuzzy Particle Swarm Optimization,FPSO）。该算法以模糊物元分析理论为依据,采用复合模糊物元与基准模糊物元之间的欧式贴近度作为适应度值引导粒子群算法的进化,并引入具有容量限制的外部存储器保留较优的Pareto非支配解以供决策者选择。此外,构建了优化目标为最大完工时间、设备总负荷、加工成本、最大设备负荷与加工质量的高维多目标优化模型,并以Kacem基准问题与实际生产数据为例进行仿真模拟与对比分析。结果表明,该算法具有良好的收敛性且搜索到的非支配解分布性较好,能够有效地应用于求解高维多目标柔性作业车间调度问题。     

An effective heuristic for flexible job-shop scheduling problem with maintenance activities

Most production scheduling problems, including the standard flexible job-shop scheduling problem (FJSP), assume that machines are continuously available. However, in most realistic situations, machines may become unavailable during certain periods due to preventive maintenance (PM). In this paper, a flexible job-shop scheduling problem with machine availability constraints is considered. Each machine is subject to preventive maintenance during the planning period and the starting times of maintenance activities are either flexible in a time window or fixed beforehand. Moreover, two cases of maintenance resource constraint are considered: sufficient maintenance resource available or only one maintenance resource available. To deal with this variant FJSP problem with maintenance activities, a filtered beam search (FBS) based heuristic algorithm is proposed. With a modified branching scheme, the machine availability constraint and maintenance resource constraint can be easily incorporated into the proposed algorithm. Simulation experiments are conducted on some representative problems. The results demonstrate that the proposed filtered beam search based heuristic algorithm is a viable and effective approach for the FJSP with maintenance activities.