Single-machine batch delivery scheduling with an assignable common due date and controllable processing times

We consider single-machine batch delivery scheduling with an assignable common due date and controllable processing times, which vary as a convex function of the amounts of a continuously divisible common resource allocated to individual jobs. Finished jobs are delivered in batches and there is no capacity limit on each delivery batch. We first provide an O(n⁵) dynamic programming algorithm to find the optimal job sequence, the partition of the job sequence into batches, the assigned common due date, and the resource allocation that minimize a cost function based on earliness, tardiness, job holding, due date assignment, batch delivery, and resource consumption. We show that a special case of the problem can be solved by a lower-order polynomial algorithm. We then study the problem of finding the optimal solution to minimize the total cost of earliness, tardiness, job holding, and due date assignment, subject to limited resource availability, and develop an O(nlog n) algorithm to solve it.     

Scheduling a batching machine with convex resource consumption functions

In various industries jobs undergo a batching, or burn in, process where different tasks are grouped into batches and processed simultaneously. The processing time of each batch is equal to the longest processing time among all jobs contained in the batch. All to date studies dealing with batching machines have considered fixed job processing times. However, in many real life applications job processing times are controllable through the allocation of a limited resource. The most common and realistic model assumes that there exists a non-linear and convex relationship between the amount of resource allocated to a job and its processing time. The scheduler?s task when dealing with controllable processing times is twofold. In addition to solving the sequencing problem, one must establish an optimal resource allocation policy. We combine these two widespread models on a single machine setting, showing that both the makespan and total completion time criteria can be solved in polynomial time. We then show that our proposed approach can be applied to general bi-criteria objective comprising of the makespan and the total completion time.     

Single-machine scheduling with learning effect and resource-dependent processing times

We consider resource allocation scheduling with learning effect in which the processing time of a job is a function of its position in a sequence and its resource allocation. The objective is to find the optimal sequence of jobs and the optimal resource allocation separately. We concentrate on two goals separately, namely, minimizing a cost function containing makespan, total completion time, total absolute differences in completion times and total resource cost; minimizing a cost function containing makespan, total waiting time, total absolute differences in waiting times and total resource cost. We analyse the problem with two different processing time functions. For each combination of these, we provide a polynomial time algorithm to find the optimal job sequence and resource allocation.     

Heuristics for minimizing total completion time and maximum lateness on identical parallel machines with setup times

This paper aims at minimizing the total completion time together with the maximum lateness. Jobs are processed by parallel machines in batches. A setup is required before processing a batch, which is common for all jobs in the batch. Jobs are continuously processed after the setup time. The processing length of a batch is the sum of the setup time and processing times of the jobs it contains. Due to the availability constraint, the completion time of a job is the time when a batch is totally processed. Considering due dates, the jobs need to be processed in a way that the total completion time and the maximum lateness are minimized. This problem is a kind of NP-hard so first we present a constructive heuristic to solve the problem. Then we propose a genetic algorithm whose initial population is formed by using the heuristic approach. Computational experiments are carried out to evaluate the performance of the proposed algorithms.     

Single‐machine common flow allowance scheduling with aging effect,resource allocation,and a rate‐modifying activity

In this paper, we consider scheduling of deteriorating jobs on a single machine with slack (SLK) due date assignment, resource allocation, and a rate‐modifying activity. The rate‐modifying activity can change jobs’ processing rates such that the actual processing time of a job depends on whether the job is processed before or after the rate‐modifying activity. In addition, the actual processing time of a job also depends on its position in a processing sequence (i.e., the aging effect) and the amount of resource allocated to it. The objective is to determine the optimal sequence, optimal common flow allowance, optimal resource allocation, and optimal location of the rate‐modifying activity to minimize a total penalty function comprising the earliness, tardiness, common flow allowance, and resource allocation costs. We consider two variants of the problem associated with two different processing time functions and provide a polynomial‐time algorithm to solve each variant.     

Two-machine no-wait flowshop scheduling with learning effect and convex resource-dependent processing times

Two-machine no-wait flowshop scheduling problems in which the processing time of a job is a function of its position in the sequence and its resource allocation are considered in the study. The primary objective is to find the optimal sequence of jobs and the optimal resource allocation separately. Here we propose two separate models: minimizing a cost function of makespan, total completion time, total absolute differences in completion times and total resource cost; minimizing a cost function of makespan, total waiting time, total absolute differences in waiting times and total resource cost. Since each model is strongly NP-hard, we solve both models by breaking them down to two sub-problems, the optimal resource allocation problem for any job sequence and the optimal sequence problem with its optimal resource allocation. Specially, we transform the second sub-problem into the minimum of the bipartite graph optimal matching problem (NP-hard), and solve it by using the classic KM (Kuhn–Munkres) algorithm. The solutions of the two sub-problems demonstrate that the target problems remain polynomial solvable under the proposed model.     

Single-machine due-window assignment and scheduling with resource allocation,aging effect,and a deteriorating rate-modifying activity

We consider single-machine scheduling with a common due-window and a deteriorating rate-modifying activity. We assume that the processing time of a job is a function of the amount of a resource allocated to it, its position in the processing sequence, and its aging effect. The objective is to minimize the total cost, which is a function of earliness, tardiness, due-window starting time, due-window size, and resource consumption. We consider two models of the job processing time function and provide polynomial-time solution algorithms for the corresponding problems. We also give a more efficient solution algorithm for a special case of the second problem.     

面向Dataflow的异构集群混合式资源调度框架研究

Dataflow模型的使用,使得大数据计算的批处理和流处理融合为一体.但是,现有的针对大数据计算的集群资源调度框架,要么面向流处理,要么面向批处理,不适合批处理与流处理作业共享集群资源的需求.另外,GPU用于大数据分析计算时,由于缺乏有效的CPU-GPU资源解耦方式,降低了资源使用效率.在分析现有的集群资源调度框架的基础上,设计并实现了一种可以感知批处理/流处理应用的混合式资源调度框架HRM.它以共享状态架构为基础,采用乐观封锁协议和悲观封锁协议相结合的方式,确保流处理作业和批处理作业的不同资源要求.在计算节点上,提供CPU-GPU资源的灵活绑定,采用队列堆叠技术,不但满足流处理作业的实时性需求,也减少了反馈延迟并实现了GPU资源的共享.通过模拟大规模作业的调度,结果显示, HRM的调度延迟只有集中式调度框架的75%左右;使用实际负载测试,批处理与流处理共享集群时,使用HRM调度框架, CPU资源利用率提高25%以上;而使用细粒度作业调度方法,不但GPU利用率提高2倍以上,作业的完成时间也能够减少50%左右.     

Unrelated parallel machine scheduling with setup times and a total weighted tardiness objective

This paper presents several search heuristics and their performance in batch scheduling of parallel, unrelated machines. Identical or similar jobs are typically processed in batches in order to decrease setup times and/or processing times. The problem accounts for allotting batched work parts into unrelated parallel machines, where each batch consists of a fixed number of jobs. Some batches may contain different jobs but all jobs within each batch should have an identical processing time and a common due date. Processing time of each job of a batch is determined according to the machine group as well as the batch group to which the job belongs. Major or minor setup times are required between two subsequent batches depending on batch sequence but are independent of machines. The objective of our study is to minimize the total weighted tardiness for the unrelated parallel machine scheduling. Four search heuristics are proposed to address the problem, namely (1) the earliest weighted due date, (2) the shortest weighted processing time, (3) the two-level batch scheduling heuristic, and (4) the simulated annealing method. These proposed local search heuristics are tested through computational experiments with data from dicing operations of a compound semiconductor manufacturing facility.     

Grid resource brokering algorithms enabling advance reservations and resource selection based on performance predictions

We present algorithms, methods, and software for a Grid resource manager, that performs resource brokering and job scheduling in production Grids. This decentralized broker selects computational resources based on actual job requirements, job characteristics, and information provided by the resources, with the aim to minimize the total time to delivery for the individual application. The total time to delivery includes the time for program execution, batch queue waiting, and transfer of executable and input/output data to and from the resource. The main features of the resource broker include two alternative approaches to advance reservations, resource selection algorithms based on computer benchmark results and network performance predictions, and a basic adaptation facility. The broker is implemented as a built-in component of a job submission client for the NorduGrid/ARC middleware.     

极小化加权完工时间和的无界批量机器并行调度问题

考虑无界批量机器并行调度中极小化加权完工时间和问题.设有n个工件和m台批加工同型机.每个工件具有一个正权因子、一个释放时间和一个加工时间.每台机器可以同时加工B≥n个工件.一个批次的加工时间是该批次所包含的所有工件的加工时间的最大者.在同一批次中加工的工件有相同的完工时间,即它们的共同开始时间加上该批次的加工时间.给出了一个多项式时间近似方案(PTAS).     

Scheduling jobs with deterioration effect and controllable processing time

This article considered the single machine scheduling with controllable processing time (resource allocation) and deterioration effect concurrently. It discussed the minimization of three objectives, which involve the weighted sum of the makespan and the total resource consumption cost, the total resource consumption cost under the condition that the makespan (total flow time) is restricted to a fixed constant and the optimal resource allocation and the optimal job sequence is what we need to make decision. Considering the makespan constraint, it proved that these problems can be solved in polynomial time. A special case of the last problem can be solved in polynomial time with respect to the total flow time constraint.

     

面向运行时间预测和容错感知的网格资源分配

提出与描述了一种面向任务运行时间预测和容错感知（Fault-Aware）的网格资源分配策略,采用主动容错的方式,在资源出错之前尽量提前避免它出错或异常的情况发生。该策略把网格中任务的运行时间（runtime）预测和资源的在线时间（uptime）预测结合起来,相对于普通的调度策略具有比较高的资源利用率。在具体的CoBRA网格中间件中实现了该容错感知调度,描述了实现该容错感知调度策略模块的功能。测试过程中选择了睡眠任务技术,划分四种不同的场景进行实验,把该容错感知资源分配与普通的FCFS调度策略进行比较,结果证明在可变化的资源可用性的情况下系统可以加快应用的整体执行时间,具有很小的偏差。     

Minimizing the makespan on a batch machine with non-identical job sizes: an exact procedure

A batch processing machine can simultaneously process several jobs forming a batch. This paper considers the problem of scheduling jobs with non-identical capacity requirements, on a single-batch processing machine of a given capacity, to minimize the makespan. The processing time of a batch is equal to the largest processing time of any job in the batch. We present some dominance properties for a general enumeration scheme and for the makespan criterion, and provide a branch and bound method. For large-scale problems, we use this enumeration scheme as a heuristic method.Scope and purposeUsually in classical scheduling problems, a machine can perform only one job at a time. Although, one can find machines that can process several jobs simultaneously as a batch. All jobs of a same batch have common starting and ending times. Batch processing machines are encountered in many different environments, such as burn-in operations in semiconductor industries or heat treatment operations in metalworking industries. In the first case, the capacity of the machine is defined by the number of jobs it can hold. In the second case, each job has a certain capacity requirement and the total size of a batch cannot exceed the capacity of the machine. Hence, the number of jobs contained in each batch may be different. In this paper, we consider this second case (which is more difficult) and we provide an exact method for the makespan criterion (minimizing the last ending time).     

Minimizing Mean Completion Time in a Batch Processing System

We consider batch processing jobs to minimize the mean completion time. A batch processing machine can handle up to $B$ jobs simultaneously. Each job is represented by an arrival time and a processing time. Jobs processed in a batch have the same completion time, i.e., their common starting time plus the processing time of their longest job. For batch processing, non-preemptive scheduling is usually required and we discuss this case. The batch processing problem reduces to the ordinary uniprocessor system scheduling problem if $B=1$. We focus on the other extreme case $B=+\infty$. Even for this seemingly simple extreme case, we are able to show that the problem is NP-hard for the weighted version. In addition, we establish a polynomial time algorithm for a special case when there are only a constant number of job processing times. Finally, we give a polynomial time approximation scheme for the general case.     

Single-machine scheduling to minimize total convex resource consumption with a constraint on total weighted flow time

In this paper, we consider single-machine scheduling problem in which processing time of a job is described by a convex decreasing resource consumption function. The objective is to minimize the total amount of resource consumed subject to a constraint on total weighted flow time. The optimal resource allocation is obtained for any arbitrary job sequence. The computational complexity of the general problem remains an open question, but we present and analyze some special cases that are solvable by using polynomial time algorithms. For the general problem, several dominance properties and some lower bounds are derived, which are used to speed up the elimination process of a branch-and-bound algorithm proposed to solve the problem. A heuristic algorithm is also proposed, which is shown by computational experiments to perform effectively and efficiently in obtaining near-optimal solutions. The results show that the average percentage error of the proposed heuristic algorithm from optimal solutions is less than 3%.     

A bicriterion approach to time/cost trade-offs in scheduling with convex resource-dependent job processing times and release dates

This paper presents a bicriterion analysis of time/cost trade-offs for the single-machine scheduling problem where both job processing times and release dates are controllable by the allocation of a continuously nonrenewable resource. Using the bicriterion approach, we distinguish between our sequencing criterion, namely the makespan, and the cost criterion, the total resource consumed, in order to construct an efficient time/cost frontier. Although the computational complexity of the problem of constructing this frontier remains an open question, we show that the optimal job sequence is independent of the total resource being used; thereby we were able to reduce the problem to a sequencing one. We suggest an exact dynamic programming algorithm for solving small to medium sizes of the problem, while for large-scale problems we present some heuristic algorithms that turned out to be very efficient. Five different special cases that are solvable by using polynomial time algorithms are also presented.     

Tabu search heuristic for two-machine flowshop with batch processing machines

Batch processing machines are frequently encountered in many industrial environments. A batch processing machine is one which can process several jobs simultaneously as a batch. The processing time of a batch is equal to the largest processing time of any job in the batch. This study deals with the problem of scheduling jobs in a flowshop with two batch processing machines such that the makespan is minimized. A heuristic based on Tabu search (TS) technique is proposed. The proposed heuristic is compared with a heuristic based on mixed integer linear programming (MILP). Because the complexity of the MILP-based heuristic is depended on the number of job batches, the comparison is under up-to-eight batches problem. In order to measure the proposed TS-based heuristic in larger batch problem, the relative error percentage with the lower bound (REP_LB) is used. The results show that the proposed heuristic is efficient and effective for the problems with relative large job sizes.     

Scheduling a batch processing machine with incompatible job families

The problem of scheduling batch processors is important in some industries and, at a more fundamental level, captures an element of complexity common to many practical scheduling problems. We describe a branch and bound procedure applicable to a batch processor model with incompatible job families. Jobs in a given family have identical job processing times, arbitrary job weights, and arbitrary job sizes. Batches are limited to jobs from the same family. The scheduling objective is to minimize total weighted completion time. We find that the procedure returns optimal solutions to problems of up to about 25 jobs in reasonable CPU time, and can be adapted for use as a heuristic for larger problems.     

Unbounded parallel-batching scheduling with two competitive agents

We consider the scheduling problems arising when two agents, each with a family of jobs, compete to perform their respective jobs on a common unbounded parallel-batching machine. The batching machine can process any number of jobs simultaneously in a batch. The processing time of a batch is equal to the maximum processing time of the jobs in the batch. Two main categories of batch processing based on the compatibility of job families or agents are distinguished. In the case where job families are incompatible, jobs from different families cannot be placed in the same processing batch while all jobs can be placed in the same processing batch when job families are compatible. The goal is to find a schedule for all jobs of the two agents that minimizes the objective of one agent while keeping the objective of the other agent below or at a fixed value Q. Polynomial-time and pseudo-polynomial-time algorithms are provided to solve various combinations of regular objective functions for the scenario in which job families are either incompatible or compatible.