Adaptive checkpointing strategy to tolerate faults in economy based grid

In this paper, we develop a fault tolerant job scheduling strategy in order to tolerate faults gracefully in an economy based grid environment. We propose a novel adaptive task checkpointing based fault tolerant job scheduling strategy for an economy based grid. The proposed strategy maintains a fault index of grid resources. It dynamically updates the fault index based on successful or unsuccessful completion of an assigned task. Whenever a grid resource broker has tasks to schedule on grid resources, it makes use of the fault index from the fault tolerant schedule manager in addition to using a time optimization heuristic. While scheduling a grid job on a grid resource, the resource broker uses fault index to apply different intensity of task checkpointing (inserting checkpoints in a task at different intervals). To simulate and evaluate the performance of the proposed strategy, this paper enhances the GridSim Toolkit-4.0 to exhibit fault tolerance related behavior. We also compare “checkpointing fault tolerant job scheduling strategy” with the well-known time optimization heuristic in an economy based grid environment. From the measured results, we conclude that even in the presence of faults, the proposed strategy effectively schedules grid jobs tolerating faults gracefully and executes more jobs successfully within the specified deadline and allotted budget. It also improves the overall execution time and minimizes the execution cost of grid jobs.     

基于网格资源预测的任务优先级调度算法

根据网格工作流中任务的依赖关系和截止时间,以及资源的有效度和MIPS（每秒百万条指令）,提出基于网格资源预测的任务优先级调度算法。把网格任务工作流抽象为有向无环图,找到该工作流的关键路径,计算每个任务的最迟开始执行时间,作为任务的优先级。在算法中考虑用户的要求和资源的类型,以及任务调度失败后重新分配的问题。实验验证了该算法的有效性。     

Utility-driven solution for optimal resource allocation in computational grid

Optimal resource allocation is a complex undertaking due to large-scale heterogeneity present in computational grid. Traditionally, the decision based on certain cost functions has been used in allocating grid resource as a standard method that does not take resource access cost into consideration. In this paper, the utility function is presented as a promising method for grid resource allocation. To tackle the issue of heterogeneous demand, the user's preference is represented by utility function, which is driven by a user-centric scheme rather than system-centric parameters adopted by cost functions. The goal of each grid user is to maximize its own utility under different constraints. In order to allocate a common resource to multiple bidding users, the optimal solution is achieved by searching the equilibrium point of resource price such that the total demand for a resource exactly equals the total amount available to generate a set of optimal user bids. The experiments run on a Java-based discrete-event grid simulation toolkit called GridSim are made to study characteristics of the utility-driven resource allocation strategy under different constraints. Results show that utility optimization under budget constraint outperforms deadline constraint in terms of time spent, whereas deadline constraint outperforms budget constraint in terms of cost spent. The conclusion indicates that the utility-driven method is a very potential candidate for the optimal resource allocation in computational grid.     

基于效益函数的网格任务调度算法

在动态、异构、分布广泛的网格环境中，对资源的调度是一个非常复杂而重要且具有挑战性的问题。本文针对网格环境中的动态性特点，特别是用户QoS要求的动态变化性，提出了一种基于效益函数的网格任务调度算法，并采用GridSim模拟器分别对该调度算法和模拟器自带的代价最优和时间最优的网格任务调度算法进行模拟。实验的结果表明：该调度算法更能体现用户对QoS要求的动态变化；在系统完成相同数量的网格任务时，消耗相同时间的情况下，该调度算法在代价上优于基于时间优化的调度算法；而花费相同预算的情况下，在时间上优于基于代价优化的调度算法。     

副版本不可抢占的全局容错调度算法

容错是硬实时系统的关键能力,容错调度算法可以在有错误发生的情况下满足任务的实时性需求.在主副版本机制的容错调度算法中,主版本出错后留给副版本运行的时间窗口小,副版本容易错失截止期.针对副版本需要快速响应的问题,提出副版本不可抢占的全局容错调度算法FTGS-NPB（fault-tolerant global scheduling with non-preemptive backups）,赋予副版本全局最高优先级,使副版本在主版本出错后可以立刻获得处理器资源,并且在运行过程中不会被其他任务抢占.这样,副版本可以在最短时间内响应.分别基于截止期分析和响应时间分析建立了FTGS-NPB的可调度性测试,并分析了两种可调度性测试分别适用于不同的优先级分配算法.仿真实验结果表明,FTGS-NPB可以有效地减少实现容错的代价.     

QoS-based Task Group Deployment on Grid by Learning the Performance Data

Overhead of executing fine-grain tasks on computational grids led to task group or batch deployment in which a batch is resized according to the characteristics of the tasks, designated resource, and the interconnecting network. An economic grid demands an application to be processed within the given budget and deadline, referred to as the quality of service (QoS) requirements. In this paper, we increase the task success rate in an economic grid by optimally mapping the tasks to the resources prior to the batch deployment. The task-resource mapping (Advance QoS Planning) is decided based on QoS requirement and by mining the historical performance data of the application tasks using a genetic algorithm. The mapping is then used to assist in creating the task groups. Practical experiments are conducted to validate the proposed method and suggestions are given to implement our method in a cloud environment as well as to process real-time tasks.     

Multi-QoS constrained and Profit-aware scheduling approach for concurrent workflows on heterogeneous systems

The execution of a workflow application can result in an imbalanced workload among allocated processors, ultimately resulting in a waste of resources and a higher cost to the user. Here, we consider a dynamic resource management system in which processors are reserved not for a job but only to run a task, thus allowing a higher resource usage rate. This paper presents a scheduling algorithm that manages concurrent workflows in a dynamic environment in which jobs are submitted by users at any moment in time, on shared heterogeneous resources, and constrained to a specified budget and deadline for each job. Recent research attempted to propose dynamic strategies for concurrent workflows but only addressed fairness in resource sharing among applications while minimizing the execution time. The Multi-QoS Profit-Aware scheduling algorithm (MQ-PAS) proposed here is able to increase the profit achieved by the provider by considering the budget available for each job to define tasks priorities. We study the scalability of the algorithm with different types of workflows and infrastructures. The experimental results show that our strategy improves provider revenue significantly and obtains comparable successful rates of completed jobs.     

Utility-based scheduling for grid computing under constraints of energy budget and deadline

With recent advances in computing and communication technologies enabling mobile devices more powerful, the scope of Grid computing has been broadened to include mobile and pervasive devices. Energy has become a critical resource in such devices. So, battery energy limitation is the main challenge towards enabling persistent mobile grid computing. In this paper, we address the problem of energy constrained scheduling scheme for the grid environment. There is a limited energy budget for grid applications. The paper investigates both energy minimization for mobile devices and grid utility optimization problem. We formalize energy aware scheduling using nonlinear optimization theory under constraints of energy budget and deadline. The paper also proposes distributed pricing based algorithm that is used to tradeoff energy and deadline to achieve a system wide optimization based on the preference of the grid user. The simulations reveal that the proposed energy constrained scheduling algorithms can obtain better performance than the previous approach that considers both energy consumption and deadline.     

可靠的网格作业调度机制

针对网格环境的动态性特征,提出了一种可靠的网格作业调度机制(DGJS)。按照作业完成时间期限,DGJS将作业分为：高QoS级、低QoS级和无QoS级,不同QoS级作业有不同的调度优先权;基于资源可用性预测,DGJS采用基于可靠性代价的作业调度策略,将作业尽可能调度到可靠性高的资源节点;另外,DGJS对不同QoS级作业采用不同的容错策略,在保证故障容错的同时,节省网格资源。实验表明：在动态的网格环境下,较之传统的网格作业调度算法,DGJS提高了作业成功率,减少了作业完成时间。     

基于动态备份的容错网格任务调度*

提出了一种基于自适应备份的网格容错任务调度算法:最高百分之k备份算法.该算法对任务的安全需求和资源的信任等级进行匹配,在系统安全等级较低并且网络和主机可能失效的网格环境中进行容错任务调度.调度时,该算法根据整个网格系统的安全状况,对具有最高安全需求的百分之k的任务进行动态备份,任务备份数根据系统安全状况自适应变化,并对失败的任务重新调度.仿真结果表明,该算法可以有效提高不安全网格环境下的任务调度成功率,具有很好的容错性和可扩展性,优于固定备份数的网格任务调度算法.     

Utility-based QoS optimisation strategy for multi-criteria scheduling on the grid

The paper presents quality of service (QoS) optimisation strategy for multi-criteria scheduling on the grid, based on a mathematical QoS model and a distributed iterative algorithm. Three QoS criteria are considered, namely payment, deadline and reliability, which are formulated as utility function. The optimisation problem is split into two parts: task optimisation performed on behalf of the user and resource optimisation performed on behalf of the grid. The strategy employs three types of agents: task agents responsible for task optimisation, computation resource and network resource agents responsible for resource optimisation. The agents apply economic models for optimisation purposes. Dynamic programming is used to optimise the total system utility function in terms of an iterative algorithm. The objective of multi-criteria scheduling is to maximise the global utility of the system. This paper proposes an iterative scheduling algorithm that is used to perform QoS optimisation-based multi-criteria scheduling. The proposed QoS optimisation-based multi-criteria scheduling problem solution has been practically examined by simulation experiments.     

云平台下基于截止时间的自适应调度策略

针对在共享集群中进行任务调度时,无法兼顾任务的响应速度与任务完成时间的问题,提出一种基于截止时间的自适应调度算法。该算法以用户提交的截止时间为依据,根据任务的执行进度自适应地分配适当的计算资源。不同于传统调度方式里由用户提交固定资源参数,该算法在资源约束的情况下会对优先级高的任务进行抢占式调度以保证服务质量（QoS）,并在抢占过程结束后额外分配资源补偿被抢占的任务。在Spark平台进行的任务调度实验结果显示,与另一种资源协调者（YARN）框架下的调度算法相比,所提算法能严格地控制短任务的响应速度,并使长作业的任务完成时间缩短35%。     

一种多QoS目标约束的云计算任务调度策略

针对云计算环境下大量用户任务请求各异的服务质量（Quality of Service, QoS）调度目标要求,通过综合考虑云用户任务的截止时间底线、调度预算等QoS目标约束条件以及各类可用资源的性能参数,对任务调度的多QoS目标约束条件进行形式化建模,基于构造的隶属度函数将多QoS目标约束的优化求解问题转化成一个单目标约束的优化问题,对转化后的单目标约束优化问题进行近似求解,最终提出一种多QoS目标约束的云计算任务调度策略。在CloudSim模拟器上的仿真结果表明,提出的多QoS目标约束的云计算任务调度策略总体上优于传统的Min-min算法以及改进的以QoS为导向的Min-min算法。     

异构分布式实时系统中对具有前后依赖关系任务的基于动态可变调度距离容错调度算法

目前的主副版本容错调度算法大多没有考虑任务间的前后依赖关系,但实际中很多任务是具有前后依赖关系的。本文提出了一种基于主副版本动态可变调度距离的任务容错调度算法,该技术通过比较任务间的最晚开始执行时间与最早开始执行时间的差值,安排任务副版本的调度,并且基于此设计了可用于具有前后依赖关系任务调度可重叠技术。本文提出的基于动态可变调度距离的容错调度算法在尽可能让任务最早完成的情况下,提高系统的可靠性,并且优先调度关键路径任务,降低了系统的容错开销。最后通过实验证明本文算法的有效性和优异性。     

基于用户激励的共享单车调度策略

针对共享单车的调度问题,在考虑预算限制、用户最大步行距离限制、用户时空需求以及共享单车分布动态变化的情况下,提出一种用户激励下的共享单车调度策略,以达到提高共享单车平台长期用户服务率的目的。该调度策略包含任务生成算法、预算分配算法和任务分配算法。在任务生成算法中,使用长短期记忆（LSTM）网络预测用户未来的单车需求量;在预算分配算法中,采用深度策略梯度（DDPG）算法来设计预算分配策略;任务分配完预算后,需要将任务分配给用户执行,因此在任务分配算法中使用贪心匹配策略来进行任务分配。基于摩拜单车的数据集进行实验,并把所提策略分别与无预算限制的调度策略（即平台不受预算限制,可以使用任意金钱激励用户将车骑行至目标区域）、贪心的调度策略、卡车拖运下的调度策略以及未进行调度的情况进行对比。实验结果表明,与贪心调度策略和卡车托运下的调度策略相比,用户激励下的共享单车调度策略能有效提高共享单车系统中的用户服务率。     

多维QoS指导的DBC最优算法

目前应用于网格的一些调度算法过于简单，不能满足对QoS的多样化需求，比如DBC（deadline and budget constrained）调度算法只支持两维的QoS需求，即截止期限（deadline）和预算（budge）。而对于真正的网格应用，用户与系统之间的交互应该加强，用户应能对提交的工作提出多种多样的QoS需求。在对传统DBC算法进行优化的基础上，提出了“多维QoS指导的DBC最优算法”，以确保搜索到所有满足用户需求的资源，不仅包括价格、时间最优，而且满足他们自己定义的专有QoS需求。为了测试这一最优算法，所做的模拟实验是以上海网格环境中各高性能结点的数据信息作为参数。     

基于贝叶斯策略的网格资源分配方法

考虑网格应用QoS需求,以最大化网格系统的经济收益为目标,提出了一种基于贝叶斯策略的网格资源分配方法。该方法基于价格可代表资源QoS综合性能的思想,利用历史QoS匹配记录,运用朴素贝叶斯定理根据用户提交的价格参数来分配与其级别相对应的符合要价范围资源,并优先考虑QoS水平较高的任务,将当前时刻QoS水平较高的资源预留给下一时刻到达的QoS水平较高的任务,而忽略当前时刻QoS水平较低的任务。实验结果表明,该资源分配方法不仅能有效地保障用户QoS,而且能使网格系统获得较大的经济收益。     

一种多重约束下确保成功率的云工作流调度方法

为提高多重约束下的调度成功率,提出一种满足期限和预算双重约束的云工作流调度算法。将可行工作流调度方案求解分解为工作流结构分层、预算分配、期限分配、任务选择和实例选择。工作流结构分层将所有工作流任务划分层次形成包任务,以提高并行执行程度;预算分配对整体预算在层次间进行分割;期限分配将全局期限在不同层次间分割;任务选择基于任务最早开始时间确定优先级,得到任务调度次序;实例选择根据时间和代价均衡因子,获取任务执行最佳实例。仿真结果证明,该算法在调度成功率、同步优化工作流执行时间与执行代价上相较对比算法更好。     

基于层次化的网格资源三层调度模型

在分析现有的资源调度方案及模型的基础上,提出了基于层次化的网格资源三层调度模型．它由主调度器、次级调度器和计算节点组成。主调度器根据任务的性质和需求,并参考下层次级调度器的执行情况,将部分任务分发到各次级调度器上,实现了主调度器与次级调度器之间的并行工作。基于该模型提出轮循任务分发策略。通过分析和模拟．该资源调度模型及任务分发策略在调度性能上明显优于集中式调度方案。     

超立方体多处理机系统中基于扩展最优通路矩阵的容错路由

该文在高峰等文章的基础上，提出了针对超立方体结构多处理机系统的扩展最优通路矩阵（Extended Optimal Path Matrices,EOPMs）的概念，并给出了一个建立EIPMs的算法和基于EOPMs的容错路由算法，证明了基于EOPMs的容错路由算法是基于扩展安全向量（ESVs）^[13]和基于最优通路矩阵（OPMs)^[14]容错路由算法的扩展，与原文相比，该算法的存储开销与OPMs,相同，但记录的最优通路的信息，包含了原文所记录的最优通路的信息，使搜索最优通路的能力比它们有进一步的提高。