基于模糊聚类的云任务调度算法

为了更好地实践云计算提供廉价按需服务的宗旨,提出了一种在模糊聚类基础上,基于两级调度模式的任务调度(FCTLBS,fuzzy clustering and two level based task scheduling)算法,新算法设置用户调度和任务调度2个等级。对资源进行性能模糊聚类;根据任务参数计算资源偏好,使不同偏好任务在不同聚类中选择,缩小了选择范围,更好地反映了任务需求。仿真实验表明,本算法较之同类算法具备一定的优越性。     

云环境下基于Min-Min改进的任务调度算法

在Min-Min的基础上,针对所存在的缺陷,提出了一种负载均衡的改进算法.仿真实验表明,在一定条件下,改进后的算法比传统的算法有一定的提高.     

一种基于动态关键路径的云工作流调度算法探讨

云工作流调度算法是信息传输和沟通的主要方式。为适应当前活动实践需求,将云计算作为计算机运转调节的主要手段,合理进行云环境下工作调度因素的调节,在探索信息技术沟通渠道创新中发挥着不可忽视的作用。文章结合国内技术分析的基本情况,首先阐述了云工作流调度算法路径研究价值,其次着重从集合式工作调度、单元限制条件分析等方面,探究一种基于动态关键路径的云工作流调度算法要点,以达到明确技术关键条件,促进云工作服务手段调节革新的目的。     

An agent‐based workflow scheduling mechanism with deadline constraint on hybrid cloud environment

Summary

With the advances of cloud computing, business and scientific‐oriented jobs with certain workflows are increasingly migrated to and run on a variety of cloud environments. These jobs are often with the property of deadline constraint and have to be completed within limited time. Therefore, to schedule a job with workflow (short for workflow) with deadline constraint is increasingly becoming a crucial research issue. In this paper, we, based on previous work, propose an agent‐based workflow scheduling mechanism to schedule workflows that are with deadline constraint into federated cloud environment.

Design and Methods

We add a workflow agent into the original framework to schedule the deadline‐constraint workflow. The workflow agent can smoothly schedule workflows to the cloud system according to their required resource and automatically monitor their execution. In order to accurately predict the execution time of each task to meet deadline constraint on certain VM with given resource, we inherit the use of rough set theory to estimate execution time of task in our previous work.

Result and Discussion

A heuristic algorithm that is embedded into the workflow agent is also proposed because the problem had been shown to be NP‐complete. The mechanism also adopts dynamic job dispatching method to reduce the usage of VM and to improve the resource utilization. We also conducted experiments to evaluate the efficiency and effectiveness.

Conclusion

The experimental results show that the prediction time is very close to the real execution time and can efficiently schedule multiple scientific workflows to meet the deadline constraints simultaneously.     

基于粒子群算法的嵌入式云计算资源调度

随着移动互联网的发展,基于嵌入式设备的云计算服务成为研究热点。在国内,嵌入式云计算目前正处于探索研究阶段,云资源管理调度是嵌入式云计算的核心技术之一,其效率直接影响嵌入式云计算系统的性能。为了提高云计算性能,本文提出一种基于粒子群优化算法的云计算任务调度模型。粒子群算法中粒子位置代表可行的资源调度方案,以云计算任务完成时间及资源负载均衡度作为目标函数,通过粒子群优化算法,找出最优资源调度方案。在matlab实验平台进行了仿真,通过大量数据模拟实验表明,该模型可以快速找到最优调度方案,提高资源利用率,具有较好的实用性和可行性。     

Efficient task scheduling in cloud networks using ANN for green computing

Recently, there has been a growing emphasis on reducingenergy consumption in cloud networks and achieving green computing practices toaddress environmental concerns and optimize resource utilization. In thiscontext, efficient task scheduling minimizes energy usage and enhances overallsystem performance. To tackle the challenge ofenergy-efficient task allocation, we propose a novel approach that harnessesthe power of Artificial Neural Networks (ANN). Our Artificial neural network Dynamic Balancing (ANNDB) method is designed toachieve green computing in cloud environments. ANNDB leverages the feed-forwardnetwork architecture and a multi-layer perceptron, effectively allocatingrequests to higher-power and higher-quality virtual machines, resulting inoptimized energy utilization. Through extensive simulations, wedemonstrate the superiority of ANNDB over existing methods, including WPEG,IRMBBC, and BEMEC, in terms of energy and power efficiency. Specifically, ourproposed ANNDB method exhibits substantial improvements of 13.81%, 8.62%, and9.74% in the Energy criterion compared to WPEG, IRMBBC, and BEMEC,respectively. Additionally, in the Power criterion, the method achievesperformance enhancements of 3.93%, 4.84%, and 4.19% over the mentioned methods.The findings from this research hold significant promise for organizations seekingto optimize their cloud computing environments while reducing energyconsumption and promoting sustainable computing practices. By adopting theANNDB approach for efficient task scheduling, businesses and institutions cancontribute to green computing efforts, reduce operational costs, and make moreenvironmentally friendly choices without compromising task allocationperformance.     

云计算资源调度算法的研究与实现

在研究蚁群算法、任务分配和资源调度的基础上,提出了一种改进的蚁群资源调度算法.首先通过引入节点可信度机制在一定程度上增强了云计算资源的搜索能力和节点完成任务的成功率.然后在改进的算法中使用了信息素的局部更新机制和全局更新机制,可以有效地平衡负载.最后通过选取合适的参数利用CloudSim仿真工具对改进的资源调度算法进行实验测试,实验结果表明此算法缩短了任务的执行时间,改善了云计算资源调度的性能.     

Task scheduling mechanisms in cloud computing: A systematic review

Today, cloud computing has developed as one of the important emergent technologies in communication and Internet. It offers on demand, pay per use access to infrastructure, platforms, and applications. Due to the increase in its popularity, the huge number of requests need to be handled in an efficient manner. Task scheduling as one of the challenges in the cloud computing supports the requests for assigning a particular resource so as to perform effectively. In the resource management, task scheduling is performed where there is the dependency between tasks. Many approaches and case studies have been developed for the scheduling of these tasks. Up to now, a systematic literature review (SLR) has not been presented to discover and evaluate the task scheduling approaches in the cloud computing environment. To overcome, this paper presents an SLR‐based analysis on the task scheduling approaches that classify into (a) single cloud environments that evaluate cost‐aware, energy‐aware, multi‐objective, and QoS‐aware approaches in task scheduling; (b) multicloud environment that evaluates cost‐aware, multi‐objective, and QoS‐aware task scheduling; and (c) mobile cloud environment that is energy‐aware and QoS‐aware task scheduling. The analytical discussions are provided to show the advantages and limitations of the existing approaches.     

基于改进人工免疫算法的云计算任务调度

为了提高云计算任务调度效率,提出一种改进人工免疫算法的云计算任务调度方法。首先建立云计算任务调度的数学模型,并以任务总时间最短作为目标函数,然后采用人工免疫算法进行求解,并将粒子群优化算法作为算子嵌入人工免疫算法中,保持种群的多样性,防止局部最优解的出现,最后采用仿真实验对算法的性能进行测试。结果表明,相对于其它算法,改进人工免疫算法减少了任务的完成时间,提高了用户满意度。     

Multicriteria decision‐making techniques for avoiding similar task scheduling conflict in cloud computing

An efficient task scheduling approach shows promising way to achieve better resource utilization in cloud computing. Various task scheduling approaches with optimization and decision‐making techniques have been discussed up to now. These approaches ignored scheduling conflict among the similar tasks. The conflict often leads to miss the deadlines of the tasks. The work studies the implementation of the MCDM (multicriteria decision‐making) techniques in backfilling algorithm to execute deadline‐based tasks in cloud computing. In general, the tasks are selected as backfill tasks, whose role is to provide ideal resources to other tasks in the backfilling approach. The selection of the backfill task is challenging one, when there are similar tasks. It creates conflict in the scheduling. In cloud computing, the deadline‐based tasks have multiple parameters such as arrival time, number of VMs (virtual machines), start time, duration of execution, and deadline. In this work, we present the deadline‐based task scheduling algorithm as an MCDM problem and discuss the MCDM techniques: AHP (Analytical Hierarchy Process), VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje), and TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) to avoid similar task scheduling conflicts. We simulate the backfilling algorithm along with three MCDM mechanisms to avoid scheduling conflicts among the similar tasks. The synthetic workloads are considered to study the performance of the proposed scheduling algorithm. The mechanism suggests an efficient VM allocation and its utilization for deadline‐based tasks in the cloud environment.     

A non‐cooperative game model for reliability‐based task scheduling in cloud computing

Cloud computing is a newly emerging distributed system. Task scheduling is the core research of cloud computing which studies how to allocate the tasks among the physical nodes, so that the tasks can get a balanced allocation or each task's execution cost decreases to the minimum, or the overall system performance is optimal. Unlike task scheduling based on time or cost before, aiming at the special reliability requirements in cloud computing, we propose a non‐cooperative game model for reliability‐based task scheduling approach. This model takes the steady‐state availability that computing nodes provide as the target, takes the task slicing strategy of the schedulers as the game strategy, then finds the Nash equilibrium solution. We also design a task scheduling algorithm based on this model. It can be seen from the experiments that our task scheduling algorithm is better than the so‐called balanced scheduling algorithm.     

面向分布式环境的信号驱动任务调度算法

为优化IaaS服务的执行效率,提出面向IaaS的信号驱动任务调度算法,该算法根据IaaS模型的结构特征建立控制子系统和节点子系统,根据任务的结构特征建立任务的DAG(directed acyclic graph)调度模型,并建立各任务分片的状态转化机制及控制子系统和节点子系统间的信号通信机制。以系统间信号交互的方式驱动任务分片的状态改变,并在每一调度时刻来临时利用并行优化选择策略分配任务分片。由于本算法采用了模拟IaaS模型的双系统控制方式,使本算法与IaaS模型的分布式体系相兼容且复杂度较低。最后通过实验验证了所提算法的有效性和实用性。     

云计算环境下的资源管理研究

首先提出高性能的大规模的云计算资源是实现云计算服务的基本条件,而对庞大的资源如何进行管理和分配,是云计算服务必须解决的后继问题。其次分析云计算资源管理主要分为数据存储的资源管理,存储层,基础管理层、应用接口层和访问层构成了云存储系统的4层结构模型,云安全是存储技术的重要方面,而云资源调度则包括资源发现、调度组织、调度策略、状态评估以及对资源的再调度等。最后针对目前亟需解决的信息存储安全、服务可靠性、大规模隐私泄露以及资源的可移植性和兼容性等问题提出了相应的资源管理技术方法。     

K均值聚类在云计算的应用

相对于传统的应用部署方式,云计算是基于互联网的一种并行处理技术,提供了一个高度可扩展和按需处理的服务。任务调度一直是云计算环境中的研究热点,在云计算环境中具有重要作用。能否合理分配任务到虚拟机资源上是重要问题之一。本文通过对任务请求的资源进行分析,对不同类型的任务进行聚类,将不同类型任务通过改进贪心调度算法合理分配到虚拟机资源上。通过Cloudsim平台模拟实验表明,该算法相对于Min-Min算法在节省能耗方面有较好的效果。     

A genetic algorithm‐based task scheduling for cloud resource crowd‐funding model

With the rapid development of cloud computing, the number of cloud users is growing exponentially. Data centers have come under great pressure, and the problem of power consumption has become increasingly prominent. However, many idle resources that are geographically distributed in the network can be used as resource providers for cloud tasks. These distributed resources may not be able to support the resource‐intensive applications alone because of their limited capacity; however, the capacity will be considerably increased if they can cooperate with each other and share resources. Therefore, in this paper, a new resource‐providing model called “crowd‐funding” is proposed. In the crowd‐funding model, idle resources can be collected to form a virtual resource pool for providing cloud services. Based on this model, a new task scheduling algorithm is proposed, RC‐GA (genetic algorithm for task scheduling based on a resource crowd‐funding model). For crowd‐funding, the resources come from different heterogeneous devices, so the resource stability should be considered different. The scheduling targets of the RC‐GA are designed to increase the stability of task execution and reduce power consumption at the same time. In addition, to reduce random errors in the evolution process, the roulette wheel selection operator of the genetic algorithm is improved. The experiment shows that the RC‐GA can achieve good results.     

Crow–penguin optimizer for multiobjective task scheduling strategy in cloud computing

Task scheduling in the cloud is the multiobjective optimization problem, and most of the task scheduling problems fail to offer an effective trade‐off between the load, resource utilization, makespan, and Quality of Service (QoS). To bring a balance in the trade‐off, this paper proposes a method, termed as crow–penguin optimizer for multiobjective task scheduling strategy in cloud computing (CPO‐MTS). The proposed algorithm decides the optimal execution of the available tasks in the available cloud resources in minimal time. The proposed algorithm is the fusion of the Crow Search optimization Algorithm (CSA) and the Penguin Search Optimization Algorithm (PeSOA), and the optimal allocation of the tasks depends on the newly designed optimization algorithm. The proposed algorithm exhibits a better convergence rate and converges to the global optimal solution rather than the local optima. The formulation of the multiobjectives aims at a maximum value through attaining the maximum QoS and resource utilization and minimum load and makespan, respectively. The experimentation is performed using three setups, and the analysis proves that the method attained a better QoS, makespan, Resource Utilization Cost (RUC), and load at a rate of 0.4729, 0.0432, 0.0394, and 0.0298, respectively.     

云模型优化的QPSO算法在大数据云存储平台业务调度中的应用

QPSO算法作为最优秀的群体智能算法之一,有着较强的寻优能力,将QPSO算法用于云计算平台资源调度策略的寻优,有着明显的优势。通过对QPSO算法在云计算中的应用研究,为云计算平台效率的提升提供有效方法。文章对云模型优化的QPSO算法在大数据云存储平台业务调度中的应用进行分析与研究。     

基于特征粒子的调度算法在云计算中的应用

针对云计算中资源调度的无序性,以及虚拟机级别上负载均衡难以处理的问题,提出特征粒子调度算法。该算法能够快速、高效、有选择性地完成资源节点的筛选和调度,从而在全局上能够实现节点处理能力的均衡,以及节点资源的最佳利用。通过在模拟仿真平台(Cloud-Sim)上的模拟测试,实验结果表明,此算法能够有效地整理不同特征的云资源节点、缩短云环境下的任务平均运行时间,提高资源的利用率,并在理论上可大大降低整个云的资源消耗。     

云环境下服务信任感知的可信动态级调度方法

以社会学中的人际关系信任模型为基础,提出了一种基于服务消费者的服务满意度评价、推荐者的服务推荐和第三方服务性能反馈的可信度量模型。将用户对服务资源的信任需求和服务资源的可信度并入DLS算法得到可信动态级调度算法CTDLS,从而在计算调度级别时考虑服务资源的可信程度。模拟实验表明,该算法能有效满足任务在信任方面的服务质量需求,对提高任务调度的成功率具有实际意义。     

布谷鸟粒子群优化算法的多目标任务调度

高效的调度方法促使云计算更快更好地服务,一般采用优化算法来解决云计算中的调度问题。将布谷鸟搜索(CS)和粒子群优化(PSO)两种算法相结合,提出多目标布谷鸟粒子群优化算法(MO-CPSO),主要目的是提高云计算的服务质量。使用Cloudsim仿真工具对MO-CPSO算法的性能进行了评估。仿真结果表明,与CS、ACO和Min-Min算法相比,MO-CPSO算法使makespan、开销和截止时间违背率均最小。