Minimizing conditional-value-at-risk for stochastic scheduling problems

This paper introduces the use of conditional-value-at-risk (CVaR) as a criterion for stochastic scheduling problems. This criterion has the tendency of simultaneously reducing both the expectation and variance of a performance measure, while retaining linearity whenever the expectation can be represented by a linear expression. In this regard, it offers an added advantage over traditional nonlinear expectation-variance-based approaches. We begin by formulating a scenario-based mixed-integer program formulation for minimizing CVaR for general scheduling problems. We then demonstrate its application for the single machine total weighted tardiness problem, for which we present both a specialized l-shaped algorithm and a dynamic programming-based heuristic procedure. Our numerical experimental results reveal the benefits and effectiveness of using the CVaR criterion. Likewise, we also exhibit the use and effectiveness of minimizing CVaR in the context of the parallel machine total weighted tardiness problem. We believe that minimizing CVaR is an effective approach and holds great promise for achieving risk-averse solutions for stochastic scheduling problems that arise in diverse practical applications.     

Performance analysis of a novel traffic scheduling algorithm in slotted optical networks

This paper considers the scheduling problem in a new slotted optical network called Time-Domain Wavelength Interleaved network (TWIN). The TWIN architecture possesses interesting properties, which may offer solutions for next-generation optical networks. Besides, better Quality of Service (QoS) could be achieved in TWIN by minimizing two parameters: queueing delay and delay variance. However, to the best of our knowledge, most of the existing scheduling algorithms in TWIN ignored consideration of QoS and focused mainly on maximizing the throughput. In this paper, we formulate the scheduling problem into an Integer Linear Programming (ILP) problem and propose a novel heuristic – Destination Slot Set (DSS) algorithm to solve it fast and efficiently. Besides, we derive an analytical model for TWIN and investigate the performance of DSS in it. By means of simulations, we demonstrate that our analytical model approximates the TWIN network very well; moreover, DSS incurs smaller queueing delay and delay variance, which ensures better QoS.     

Using hybrid scheduling for the semi-autonomous formation of expert teams

Selecting and scheduling human experts to cooperatively solve a problem can be a highly complex task, given various constraints (such as what expertise is needed and when) and preferences (such as which expertise an expert most prefers to exercise). Computational agents can thus greatly help users form and schedule expert teams. This paper introduces a new formulation of the team formation and scheduling problem as a Hybrid Scheduling Problem (HSP) and compares the performance of an agent using the HSP formulation to a prior agent-based approach. We empirically demonstrate the promise of the HSP formulation and highlight how the application of HSP techniques to this problem has led us to identify important modifications to mechanisms that improve HSP solving. Finally, we summarize how the HSP formulation can support human-agent collaboration during the process of forming and scheduling expert teams.     

A multi-objective reinforcement learning algorithm for deadline constrained scientific workflow scheduling in clouds

Recently, a growing number of scientific applications have been migrated into the cloud. To deal with the problems brought by clouds, more and more researchers start to consider multiple optimization goals in workflow scheduling. However, the previous works ignore some details, which are challenging but essential. Most existing multi-objective workflow scheduling algorithms overlook weight selection, which may result in the quality degradation of solutions. Besides, we find that the famous partial critical path (PCP) strategy, which has been widely used to meet the deadline constraint, can not accurately reflect the situation of each time step. Workflow scheduling is an NP-hard problem, so self-optimizing algorithms are more suitable to solve it.In this paper, the aim is to solve a workflow scheduling problem with a deadline constraint. We design a deadline constrained scientific workflow scheduling algorithm based on multi-objective reinforcement learning (RL) called DCMORL. DCMORL uses the Chebyshev scalarization function to scalarize its Q-values. This method is good at choosing weights for objectives. We propose an improved version of the PCP strategy calledMPCP. The sub-deadlines in MPCP regularly update during the scheduling phase, so they can accurately reflect the situation of each time step. The optimization objectives in this paper include minimizing the execution cost and energy consumption within a given deadline. Finally, we use four scientific workflows to compare DCMORL and several representative scheduling algorithms. The results indicate that DCMORL outperforms the above algorithms. As far as we know, it is the first time to apply RL to a deadline constrained workflow scheduling problem.     

带有资源冲突的Seru在线并行调度算法

随着大规模定制的市场需求日趋显著,赛如生产系统(Seru production system,SPS)应运而生,逐渐成为研究和应用领域的热点.本文针对带有资源冲突的Seru在线并行调度问题进行研究,即需要在有限的空间位置上安排随动态需求而构建的若干Seru,以总加权完工时间最小为目标,决策Seru的构建顺序及时间.先基于平均延迟最短加权处理时间(Average delayed shortest weighted processing time,AD-SWPT)算法,针对其竞争比不为常数的局限性,引入调节参数,得到竞争比为常数的无资源冲突的Seru在线并行调度算法.接下来,引入冲突处理机制,得到有资源冲突的Seru在线并行调度算法,αAD-I(α-average delayed shortest weighted processing time-improved)算法,特殊实例下可通过实例归约的方法证明其竞争比与无资源冲突的情况相同.最后,通过实验,验证了在波动的市场环境下算法对于特殊实例与一般实例的优越性.     

带有资源冲突的Seru在线并行调度算法

随着大规模定制的市场需求日趋显著,赛如生产系统(Seru production system,SPS)应运而生,逐渐成为研究和应用领域的热点.本文针对带有资源冲突的Seru在线并行调度问题进行研究,即需要在有限的空间位置上安排随动态需求而构建的若干Seru,以总加权完工时间最小为目标,决策Seru的构建顺序及时间.先基于平均延迟最短加权处理时间(Average delayed shortest weighted processing time,AD-SWPT)算法,针对其竞争比不为常数的局限性,引入调节参数,得到竞争比为常数的无资源冲突的Seru在线并行调度算法.接下来,引入冲突处理机制,得到有资源冲突的Seru在线并行调度算法,αAD-I(α-average delayed shortest weighted processing time-improved)算法,特殊实例下可通过实例归约的方法证明其竞争比与无资源冲突的情况相同.最后,通过实验,验证了在波动的市场环境下算法对于特殊实例与一般实例的优越性.     

Minimizing aperiodic response times in a firm real-time environment

In certain real-time applications, ranging from multimedia to telecommunication systems, timing constraints can be more flexible than scheduling theory usually permits. In this paper, we deal with the problem of scheduling hybrid sets of tasks, consisting of firm periodic tasks (i.e. tasks with deadlines which can occasionally skip one instance) and soft aperiodic requests, which have to be served as soon as possible to achieve good responsiveness. We propose and analyze an algorithm, based on a variant of earliest-deadline-first scheduling, which exploits skips to minimize the response time of aperiodic requests. One of the most interesting features of our algorithm is that it can easily be tuned to balance performance vs. complexity, for adapting it to different application requirements. Extensive simulation experiments show the effectiveness of the proposed approach with respect to existing methods. Schedulability bounds are also derived to perform off-line analysis     

REDOM: an OO language to define and on-line manipulate regulations in the resource (re)scheduling problem

In the class of (re)scheduling problems where humans constitute the main resource, the scheduling process is influenced by a great number of complex and frequently changing regulations. The complexity and the dynamic nature of these regulations impose the need for an efficient, flexible and user-friendly way to express and manage them. A solution to this problem, in the form of an object-oriented high-level language with semantics highly-tailored to the user needs, is presented. The language, called REDOM, can be applied to different scheduling application domains with a minimum degree of effort, because it is based on a generic meta-model of the resource scheduling problem. An application programming interface facilitates REDOM integration into existing scheduling systems. REDOM is currently being utilised by the DAYSY resource management system, that is implemented as a constraint satisfaction system based on a partial test-and-generate approach. The combination of REDOM and CHIP (Constraint Handling In Prolog), which was used for the implementation of the solution generation subsystem, resulted in a highly-efficient and flexible (re)scheduling system, well-accepted by users. © 1997 John Wiley & Sons, Ltd.     

基于攻防行动链的网络对抗推演系统

网络对抗推演是在网络对抗中进行任务规划、评估决策的重要环节。针对网络对抗广维度、多目标、短猝发的特点，传统的推演系统已不能完成网络对抗推演的要求。为了解决该问题，本文设计基于攻防行动链的网络对抗推演系统。系统架构由数据库、可视化平台、攻防链构设、推演控制引擎、模型构建、应用层等子系统构成，各子系统的模块之间相互配合，驱动整体网络对抗推演系统按照推演剧情进行，并形成具有攻防博弈性的链式行动想定或构设，称之为攻防行动链。攻防行动链的提出，使推演系统能够更好地进行推演过程中的调度和决策，也为网络攻防对抗推演提供了一个参考的研究方向。     

A new optimal approach for multiple optimisation objectives grid resource allocation and scheduling

The article considers the resource allocation and scheduling problem in a grid computing environment. The article proposes system optimisation scheduling (SOS) that provides a potential solution of joint optimisation of objectives for both the resource and application layer, which combine both application-oriented and resource-oriented scheduling benefits. Grid systems will strive to find an optimal relation between user satisfaction and resource utilisation. Utility functions are used to express grid user's Quality of Service requirement, resource provider's benefit function and system's objectives. In order to verify the efficiency of the proposed scheduling algorithm, we compare the performance of application optimisation scheduling, resource optimisation scheduling, SOS with a traditional Round-Robin algorithm. The simulations study the effect of the request rate and task-to-resource ratio on the different scheduling algorithm.     

Multi-Criteria Job Scheduling in Grid Using an Accelerated Genetic Algorithm

The continuous growth of computation power requirement has provoked computational Grids, in order to resolve large scale problems. Job scheduling is a very important mechanism and a better scheduling scheme can greatly improve the efficiency of Grid computing. A lot of algorithms have been proposed to address the job scheduling problem. Unfortunately, most of them largely ignore the security risks involved in executing jobs in such an unreliable environment as Grid. This is known as security problem and it is a main hurdle to make the job scheduling secure, reliable and fault-tolerant. In this paper, we present a Genetic Algorithm with multi-criteria approach, in terms of job completion time and security risks. Although Genetic Algorithms are suitable for large search space problems such as job scheduling, they are too slow to be executed online. Hence, we changed the implementation of a traditional genetic algorithm, proposing the Accelerated Genetic Algorithm. We also present the Accelerated Genetic Algorithm with Overhead which concerns the extra overhead caused by the application of Accelerated Genetic Algorithm. Accelerated Genetic Algorithm and Accelerated Genetic Algorithm with Overhead are compared with three well-known heuristic algorithms. Simulation results indicate a substantial performance advantage of both Accelerated Genetic Algorithm and Accelerated Genetic Algorithm with Overhead.     

Scheduling streaming applications on a complex multicore platform

In this paper, we consider the problem of scheduling streaming applications described by complex task graphs on a heterogeneous multicore platform, the IBM QS 22 platform, embedding two STI Cell Broadband Engine processor. We first derive a complete computation and communication model of the platform on the basis of comprehensive benchmarks. Then we use this model to express the problem of maximizing the throughput of a streaming application on this platform. Although the problem is proven NP‐complete, we present an optimal solution based on mixed linear programming. We also propose simpler scheduling heuristics to compute mapping of the application task graph on the platform. We then come back to the platform and propose a scheduling software to deploy streaming applications on this platform. This allows us to thoroughly test our scheduling strategies on the real platform. We thus show that we are able to achieve a good speed‐up either with the mixed linear programming solution or using involved scheduling heuristics. Copyright © 2011 John Wiley & Sons, Ltd.     

基于任务-资源分配图优化选取的网格依赖任务调度

任务调度是网格应用系统获得高性能的关键.网格计算中一个大型的应用程序往往被分解为具有依赖关系的多个任务.在资源个体差异较大、广域互连的网格环境下任务间的依赖关系对传统的调度策略提出了新的挑战.任务调度的主要工作是为任务分配资源以及确定任务的执行次序,将依赖任务的可能的资源分配方案表示为任务-资源分配图（T-RAG）,在该图的基础上提出了基于T-RAG优化选取的依赖任务调度模型,将依赖任务调度问题转化为图的优化选取问题,解析最优任务-资源分配图可以同时确定资源分配方案和任务的执行次序即为最优调度方案.最后,实现了基于该模型的任务调度算法,该算法与ILHA算法的对比分析表明,在资源差异较大及任务间存在大量数据传输的情况下所提出的算法更优.     

A scheduling algorithm for applications in a cloud computing system with communication changes

This paper proposes a scheduling algorithm to solve the problem of task scheduling in a cloud computing system with time‐varying communication conditions. This algorithm converts the scheduling problem with communication changes into a directed acyclic graph (DAG) scheduling problem for existing fuzzy communication task nodes, that is, the scheduling problem for a communication‐change DAG (CC‐DAG). The CC‐DAG contains both computation task nodes and communication task nodes. First, this paper proposes a weighted time‐series network bandwidth model to solve the indefinite processing time (cost) problem for a fuzzy communication task node. This model can accurately predict the processing time of a fuzzy communication task node. Second, to address the scheduling order problem for the computation task nodes, a dynamic pre‐scheduling search strategy (DPSS) is proposed. This strategy computes the essential paths for the pre‐scheduling of the computation task nodes based on the actual computation costs (times) of the computation task nodes and the predicted processing costs (times) of the fuzzy communication task nodes during the scheduling process. The computation task node with the longest essential path is scheduled first because its completion time directly influences the completion time of the task graph. Finally, we demonstrate the proposed algorithm via simulation experiments. The experimental results show that the proposed DPSS produced remarkable performance improvement rate on the total execution time that ranges between 11.5% and 21.2%. In view of the experimental results, the proposed algorithm provides better quality scheduling solution that is suitable for scientific application task execution in the cloud computing environment than HEFT, PEFT, and CEFT algorithms.     

MobiWay应用中基于Hadoop的多目标多任务调度算法

针对Hadoop应用环境复杂、网络带宽等因素多变而影响调度算法性能的问题,提出适用于多任务多目标的Hadoop调度算法(MOSMT)。在分析已有调度算法工作原理的基础上,构建MOSMT算法的数学模型和调度策略;在负载模拟器中进行算法评估,并将MOSMT算法应用于MobiWay;对MobiWay应用中的MOSMT算法性能进行测试分析,以最少的资源和最低的时间成本完成任务的调度。通过与FIFO和Fair调度算法对比表明,该算法能够实现类似的功能,并且在处理多任务多目标时耗时更少,更为经济。     

Abductive case‐based reasoning

This article introduces abductive case‐based reasoning (CBR) and attempts to show that abductive CBR and deductive CBR can be integrated in clinical process and problem solving. Then it provides a unified formalization for integration of abduction, abductive CBR, deduction, and deductive CBR. This article also investigates abductive case retrieval and deductive case retrieval using similarity relations, fuzzy similarity relations, and similarity metrics. The proposed approach demonstrates that the integration of deductive CBR and abductive CBR is of practical significance in problem solving such as system diagnosis and analysis, and will facilitate research of abductive CBR and deductive CBR. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 957–983, 2005.     

差异工件并行批调度问题中遗传算法研究

本文考虑了遗传算法在包含差异工件的并行批处理机调度中的应用问题.工件具有不同的尺寸和到达时间.首先基于问题假设提出了一个数学规划模型,并采用BF、ERT-LPT实现工件的分批排序调度.然后考虑到这是一个NP-Hard问题,设计了新的选择、交叉、变异操作并结合遗传算法进行求解.最后通过仿真实验对比,验证了算法的有效性.     

Query language approach based on the deductive object-oriented database paradigm

The integration of data-oriented (structural), behavioral and deductive aspects is necessary in next generation information systems. The deductive object-oriented database paradigm offers a very promising starting point for the implementation of these kinds of information systems. So far in the context of this paradigm a big problem has been the lack of a query language suitable to an ordinary end user. Typically in existing proposals for deductive object-oriented databases the user has to master well both logic-based rule formulation and object-oriented programming. In this paper we introduce a set of high-level querying primitives which increases the degree of declarativeness compared to the deductive object-oriented query languages proposed so far. In terms of these primitives it is possible to offer for end users such application-specific concepts and structures whose interpretation is obvious to users but whose specification is too demanding for them. By combining these primitives in queries the user can integrate data-oriented, behavioral and deductive aspects with each other in a concept-oriented way. Our query language approach is based on the incorporation of deductive aspects to object-orientation. Among others this means that deductive aspects of objects are inherited in the specialization/generalization hierarchy like any other properties of objects.     

On the Complexity of Adjacent Resource Scheduling

We study the problem of scheduling resource(s) for jobs in an adjacent manner (ARS). The problem relates to fixed-interval scheduling on one hand, and to the problem of two-dimensional strip packing on the other. Further, there is a close relation with multiprocessor scheduling. A distinguishing characteristic is the constraint of resource-adjacency. As an application of ARS, we consider an airport where passengers check in for their flight, joining lines before one or more desks, at the desk the luggage is checked and so forth. To smoothen these operations the airport maintains a clear order in the waiting lines: a number n(f) of adjacent desks is to be assigned exclusively during a fixed time-interval I(f) to flight f. For each flight in a given planning horizon of discrete time periods, one seeks a feasible assignment to adjacent desks and the objective is to minimize the total number of involved desks. The paper explores two problem variants and relates them to other scheduling problems. The basic, rectangular version of ARS is a special case of multiprocessor scheduling. The other problem is more general and it does not fit into any existing scheduling model. After presenting an integer linear program for ARS, we discuss the complexity of both problems, as well as of special cases. The decision version of the rectangular problem remains strongly NP-complete. The complexity of the other problem is already strongly NP-complete for two time periods. The paper also determines a number of cases that are solvable in polynomial time.