混合云中基于数据保护的耦合任务调度策略

经济因素是驱动混合云负载调度和资源管理的关键因素,同时数据机密和安全性、任务依赖性等问题也对调度策略提出更高的要求。针对以上问题提出综合优化成本开销的调度策略,不仅考虑数据安全迁移和外包运行的总成本,也深入分析应用程序模型中任务依赖性调度。最后通过云仿真平台的实验仿真,并与现有的资源调度算法进行对比,实验结果表明该混合云调度策略在提高吞吐能力和降低总体成本开销方面的综合改善。     

混合云中面向数据中心的工作流数据布局方法

科学工作流是一种复杂的数据密集型应用程序.如何在混合云环境中对数据进行有效布局,是科学工作流所面临的重要问题,尤其是混合云的安全性要求给科学云工作流数据布局研究带来了新的挑战.传统数据布局方法大多采用基于负载均衡的划分模型布局数据集,该方法可以获得很好的负载平衡布局,然而传输时间并非最优.针对传统数据布局方法的不足,并结合混合云中数据布局的特点,首先设计一种基于数据依赖破坏度的矩阵划分模型,生成对数据依赖度破坏最小的划分;然后提出一种面向数据中心的数据布局方法,该方法依据划分模型将依赖度高的数据集尽量放在同一数据中心,从而减少数据集跨数据中心的传输时间.实验结果表明,该方法能够有效地缩短科学工作流运行时跨数据中心的数据传输时间.     

图书馆云建设中混合云管理策略探析

云计算作为现在数字图书馆技术发展的一种新趋势已经逐步为很多高校所认可,作为一种新型的服务系统,如何对其进行管理是目前尚待解决的问题。     

混合云工作流调度综述

在数据爆发的大背景下,传统的云计算存在本地云资源不足和扩展成本高的窘境,而最新兴起的混合云结合了资源丰富的公有云与数据敏感的私有云,成为当下研究和应用的热点方向.而工作流作为一种有吸引力的范式,其数据规模和计算规模一直都在增长,因此工作流调度是混合云研究方向中的关键问题.为此,文中首先对混合云环境下的工作流调度技术做了...     

基于混合云的虚拟学习环境初探

为了更好地支持教师教学和学生学习,教育机构需要不断优化IT基础设施、资源和业务流程。一种新兴的计算范式"云计算(cloud computing)"是最佳的解决方案,它通过提供基础设施、平台和教育服务,改变IT资源的利用和消费模式,将对教育领域产生巨大影响。文章构建一种基于混合云的虚拟学习环境,探讨实现该学习环境面临的挑战,从而提高应用程序及服务的可扩展性和可靠性,削减教育机构软硬件资源的开销,减少软件更新和数据中心维护的费用。     

红帽：这是开放混合云的时代

目前开源已经成为云计算的发展趋势,OpenStack也成为了该领域最热门的话题之一,作为OpenStack最大的贡献者,红帽的观点对于厂商和用户都有着极佳的借鉴价值。     

云计算环境下的服务调度和资源调度研究

云计算中的服务调度与资源调度对云计算的性能有重要影响,在分析现有云计算调度模式的基础上,针对云计算数据密集与计算密集的特点,提出分层调度策略以实现云计算中的服务与资源调度。分层调度策略对任务进行划分确定作业优先级,并通过数据局部性和总任务完成率对资源进行分配。数值评价部分应用分层调度与已有调度进行比较。实验结果表明,所采用的调度有效提高了资源利用率,为云服务的进一步研究提供了思路。     

时间约束下的云工作流动态混合资源调度

随着云计算的出现和云基础设施的快速部署,越来越多的大型工作流应用正在积极向云迁移.同时,如何在满足任务时间约束的前提下优化执行成本,提高资源利用率成为新的挑战.本文提出一种云工作流动态混合资源调度算法DHRS,不仅满足任务的时间约束而且在混合资源租用时取得较低的成本.首先,根据任务的优先级关系对任务进行预处理,基于概率升序对任务进行排序,并为子任务分配子截止日期;然后,依据顺序为工作流选择满足截止日期且成本较低的服务;最后,对每个服务动态选择预留资源和按需资源,基于预留资源的空闲时间段调度,进一步降低成本.在随机生成的不同的科学工作流上进行实验,并通过与现有算法对比,DHRS在满足时间约束并且降低执行成本方面具有一定的优势.     

混合云技术架构在高校信息化建设中的应用

阐述了混合云技术架构的基本概念,混合云融合了公有云和私有云,是近年来云计算的主要模式和发展方向。并针对目前高校信息化建设中云计算使用的实际情况,已经成型的云计算数据中心,需要不断扩充计算资源和存储资源,高昂的硬件成本下,如何实现可扩展性并保证高性能计算和数据安全,分析了混合云技术架构在信息化建设中应用系统具体所使用的场景和实际使用情况,主要介绍了混合云技术在校园云盘中的使用。     

基于混合云终端中间件平台的云书包设计研究

随着云计算、物联网、移动互联网等新技术的发展和信息化背景下教育云的推动,云书包的应用应运而生。但是传统的云书包的建设通常都是指针对单一平台进行开发和建设,不能满足当前跨平台云资源共享的时代要求。针对该问题提出了基于混合云终端中间件平台的云书包设计,旨在解决教育云资源一次性开发、跨平台共享的难题。详细介绍了混合云端中间件平台的关键技术,并在此基础上介绍了云书包架构和应用模式,同时分析了云书包的特点和发展前景。     

Policy based resource allocation in IaaS cloud

In present scenario, most of the Infrastructure as a Service (IaaS) clouds use simple resource allocation policies like immediate and best effort. Immediate allocation policy allocates the resources if available, otherwise the request is rejected. Best-effort policy also allocates the requested resources if available otherwise the request is placed in a FIFO queue. It is not possible for a cloud provider to satisfy all the requests due to finite resources at a time. Haizea is a resource lease manager that tries to address these issues by introducing complex resource allocation policies. Haizea uses resource leases as resource allocation abstraction and implements these leases by allocating Virtual Machines (VMs). Haizea supports four kinds of resource allocation policies: immediate, best effort, advanced reservation and deadline sensitive. This work provides a better way to support deadline sensitive leases in Haizea while minimizing the total number of leases rejected by it. Proposed dynamic planning based scheduling algorithm is implemented in Haizea that can admit new leases and prepare the schedule whenever a new lease can be accommodated. Experiments results show that it maximizes resource utilization and acceptance of leases compared to the existing algorithm of Haizea.     

Heavy traffic optimal resource allocation algorithms for cloud computing clusters

Cloud computing is emerging as an important platform for business, personal and mobile computing applications. In this paper, we study a stochastic model of cloud computing, where jobs arrive according to a stochastic process and request resources like CPU, memory and storage space. We consider a model where the resource allocation problem can be separated into a routing or load balancing problem and a scheduling problem. We study the join-the-shortest-queue routing and power-of-two-choices routing algorithms with the MaxWeight scheduling algorithm. It was known that these algorithms are throughput optimal. In this paper, we show that these algorithms are queue length optimal in the heavy traffic limit.     

Impact of user patience on auto-scaling resource capacity for cloud services

An important feature of most cloud computing solutions is auto-scaling, an operation that enables dynamic changes on resource capacity. Auto-scaling algorithms generally take into account aspects such as system load and response time to determine when and by how much a resource pool capacity should be extended or shrunk. In this article, we propose a scheduling algorithm and auto-scaling triggering strategies that explore user patience, a metric that estimates the perception end-users have from the Quality of Service (QoS) delivered by a service provider based on the ratio between expected and actual response times for each request. The proposed strategies help reduce costs with resource allocation while maintaining perceived QoS at adequate levels. Results show reductions on resource-hour consumption by up to approximately 9% compared to traditional approaches.     

A utility-based algorithm for joint uplink/downlink scheduling in wireless cellular networks

The major driver for deploying next generation wireless cellular systems is their ability to efficiently deliver resource-demanding services, many of which require symmetric communication between an uplink mobile user and a downlink mobile user that belong to the same network. In this work, we propose a utility-based joint uplink/downlink scheduling algorithm suitable for wireless services involving pairwise communication among mobile users. While most existing literature focuses on downlink-only or uplink-only scheduling algorithms, the proposed algorithm aims at ensuring a utility function that jointly captures the quality of service in terms of delay and channel quality on both links. By jointly considering the time varying channel conditions in both the uplink and the downlink directions, the proposed algorithm avoids wasting of resources and achieves notable performance gains in terms of increased number of active connections, lower packet drop rate, and increased network throughput. These gains are achieved with a tradeoff cost in terms of complexity and signaling overhead. For overhead reduction in practical scenarios, we propose an implementation over clusters within the network.