基于轮换策略的异构云资源分配算法

云计算以其按需索取、按需付费、无需预先投资的优势给用户带来极大的便利,然而静态、单一的云计算环境容易成为网络攻击的目标,给用户带来较大的安全风险。动态的虚拟机部署策略和异构的云基础设施在提升云计算环境安全性的同时会降低资源利用率。提出一种针对虚拟机轮换时的资源分配算法,将不同类型的资源抽象成维度不同的向量,并通过求解装箱问题实现资源分配中的负载平衡,同时为每个虚拟机设定驻留时间,对当前服务器的负载状态进行轮换以提升虚拟机的安全性。实验结果表明,资源动态分配算法在提高虚拟机安全性能的同时,能够减小轮换带来的负载波动。     

支持随机服务请求的云虚拟机按需物理资源分配方法

本文针对云平台按负载峰值需求配置处理机资源、提供单一的服务应用和资源需求动态变化导致资源利用率低下的问题,采用云虚拟机中心来同时提供多种服务应用.利用灰色波形预测算法对未来时间段内到达虚拟机的服务请求量进行预测,给出兼顾资源需求和服务优先等级的虚拟机服务效用函数,以最大化物理机的服务效用值为目标,为物理机内的各虚拟机动态配置物理资源.通过同类虚拟机间的全局负载均衡和多次物理机内各虚拟机的物理资源再分配,进一步增加服务请求量较大的相应类型的虚拟机的物理资源分配量.最后,给出了虚拟机中心基于灰色波形预测的按需资源分配算法ODRGWF.模拟实验表明所提算法能够有效提高云平台中处理机的资源利用率,对提高用户请求完成率以及服务质量都具有实际意义.     

一种基于服务选取的SBS云资源优化分配方法

获取满足全局优化目标的资源分配策略,是影响云环境中基于服务的软件系统(service-based software system,简称SBS)运行时优化效果的关键.然而,由于SBS内部复杂的业务逻辑关系和云环境中的资源约束,现有分配方法无法得到最优资源分配量.以满足SLA约束和最小化资源成本为目标,根据不同资源状态对应不同组件服务性能的特点,将组件服务可能的资源分配量、相应性能及成本转换为备选逻辑服务集,进而提出了一种云环境中基于服务选取的SBS资源优化分配模型,并设计了一种求解模型的混合遗传算法.算法采用整数编码以提高求解效率,并在选择算子中引入了精英保留策略,从而保证收敛到全局最优解.为提高遗传算法的局部搜索能力、加快收敛速度,以局部搜索策略改进了标准变异算子.实验验证了所提出的资源优化分配模型和求解算法的有效性,并表明:与分支定界法及精英保留策略遗传算法相比,混合遗传算法能够在较大规模的问题上快速获得具有较低资源成本的资源分配策略.     

一种面向效益均衡的网格资源预留机制

网格环境中的资源预留机制为跨站点的协同资源分配提供可靠的服务质量保证.针对传统预留机制存在本地任务QoS难以得到保障的缺陷,提出一种基于效益均衡的预留机制.该机制通过比较资源顸留收益与预留对本地任务执行所造成的负面影响来确定资源预留数量,以期取得网格任务QoS保障和本地任务QoS保障的效益均衡.模拟实验采用真实系统负载在较大规模的计算网格系统中检验了该机制的性能表现,实验结果显示,基于效益均衡的预留机制能有效提高资源利用率,同时能显著降低任务的资源费用情况.     

面向大规模云资源调度的可扩展分布式调度方法

云数据中心异构物理服务器的能耗优化资源分配问题是NP难的组合优化问题,当资源分配问题规模较大时,求解的空间比较大,很难在合理时间内求得最优解。基于分而治之的思想,从调度模式方面提出可扩展分布式调度方法,即当云数据中心待调度的物理服务器的数量比较大时,将待调度的服务器划分为若干个服务器集群,然后在每个服务器集群建立能耗优化的资源分配模型,并利用约束编程框架Choco求解模型,获得能耗最优的资源分配方式。将提出的基于可扩展分布式调度方法的能耗优化云资源调度算法与非扩展调度算法进行实验比较,实验结果表明,提出的基于可扩展分布式调度方法的能耗优化云资源调度算法在大规模云资源分配上有明显的性能优势。     

多实例云计算资源市场下超额预订决策方法

针对现有云供应商数据中心负载率低、云用户需求不确定及多样性的问题,为提高云供应商平均利润,建立了不确定需求下的多实例类型云服务超额预订模型。该模型结合实际云计算资源市场下超额预订对于云供应商负载均衡及云服务等级协议(SLA)的影响,给出超额预订的多重约束条件,提出了各实例类型数量最优分配策略。实验结果表明,采用该模型在预约未使用概率为0.25时,云供应商利润较高,数据中心负载率达到78%,最终确定了各实例类型的最优分配数量。     

小蜂窝云中功率与负载的联合优化分配算法

移动终端资源有限及本地服务基站资源不足会引起移动终端体验质量降低、卸载任务时延长的问题。为此,提出一种新的联合优化分配算法。基于小蜂窝信道质量和剩余可用计算资源建立小蜂窝云(SCC),按照信道质量和剩余可用计算资源分配负载(卸载任务)到SCC,并采用启发式算法求解发送功率的次优解。仿真结果表明,该算法在小蜂窝云计算场景中能提高无线与计算资源的利用率,同时提升用户的体验质量。     

基于拍卖的虚拟机动态供应和分配算法

当前云计算供应商通过定价算法或类似拍卖的算法来分配他们的虚拟机（VM）实例。然而,这些算法大多要求虚拟机静态供应,无法准确预测用户需求,导致资源未得到充分利用。为此,提出了一种基于组合拍卖的虚拟机动态供应和分配算法,在做出虚拟机供应决策时考虑用户对虚拟机的需求。该算法将可用的计算资源看成是“流体”资源,且这些资源根据用户请求可分为不同数量、不同类型的虚拟机实例。然后可根据用户的估价决定分配策略,直到所有资源分配完毕。基于Parallel Workload Archive（并行工作负载存档）的真实工作负载数据进行了仿真实验,结果表明该方法可保证为云供应商带来更高收入,提高资源利用率。     

云计算中基于拍卖的虚拟机动态供应和分配算法

当前云计算供应商通过定价算法或类似拍卖的算法来分配他们的虚拟机(VM)实例。然而,这些算法大多要求虚拟机静态供应,无法准确预测用户需求,导致资源未得到充分利用。为此,提出了一种基于组合拍卖的虚拟机动态供应和分配算法,在做出虚拟机供应决策时考虑用户对虚拟机的需求。该算法将可用的计算资源看成是“流体”资源,且这些资源根据用户请求可分为不同数量、不同类型的虚拟机实例。然后可根据用户的估价决定分配策略,直到所有资源分配完毕。基于并行工作负载存档(Parallel Workload Archive)的真实工作负载数据进行了仿真实验,仿真结果表明所提方法可保证为云供应商带来更高收入,提高资源利用率。     

一种新的经济网格计算任务调度控制模型

针对动态计算网格资源调度问题,基于多智能体协同技术和市场博弈机制,对计算网格资源分配技术进行了深入研究,提出了基于计算经济的网格资源调度模型,设计了消费者的效用函数,讨论了资源分配博弈中Nash 均衡解,设计了一种网格资源调度算法.仿真实验表明,资源调度算法能够为消费者的资源数量提供参考,规范消费者行为,从而使得整个资源的分配趋于合理,促进交易量.     

Multi-Layer Resource Management in Cloud Computing

The paper studies multi-layer optimization in service oriented cloud computing to optimize the utility function of cloud computing, subject to resource constraints of an IaaS provider at the resource layer, service provisioning constraints of a SaaS provider at the service layer, and user QoS (quality of service) constraints of cloud users at application layer, respectively. The multi-layer optimization problem can be decomposed into three subproblems: cloud computing resource allocation problem, SaaS service provisioning problem, and user QoS maximization problem. The proposed algorithm decomposes the global optimization problem of cloud computing into three sub-problems via an iterative algorithm. The experiments are conducted to test the efficiency of the proposed algorithm with varying environmental parameters. The experiments also compare the performance of the proposed approach with other related work.     

Mechanisms for SLA provisioning in cloud-based service providers

A challenge in cloud resource management is to design self-adaptable solutions capable to react to unpredictable workload fluctuations and changing utility principles. This paper analyzes the problem from the perspective of an Application Service Provider (ASP) that uses a cloud infrastructure to achieve scalable provisioning of its services in the respect of QoS constraints.First we draw a taxonomy of IaaS provider and use the identified features to drive the design of four autonomic service management architectures differing on the degree of control an ASP have on the system. We implemented two of this solutions and related mechanism to test five different resource provisioning policies. The implemented testbed has been evaluated under a realistic workload based on Wikipedia access traces on Amazon EC2 platform.The experimental evaluation performed confirms that: the proposed policies are capable to properly dimension the system resources making the whole system self-adaptable respect to the workload fluctuation. Moreover, having full control over the resource management plan allow to save up to the 32% of resource allocation cost always in the respect of SLA constraints.     

Matrix based proactive resource provisioning in mobile cloud environment

Mobile cloud computing is a dynamic, virtually scalable and network based computing environment where mobile device acts as a thin client and applications run on remote cloud servers. Mobile cloud computing resources required by different users depend on their respective personalized applications. Therefore, efficient resource provisioning in mobile clouds is an important aspect that needs special attention in order to make the mobile cloud computing a highly optimized entity. This paper proposes an adaptive model for efficient resource provisioning in mobile clouds by predicting and storing resource usages in a two dimensional matrix termed as resource provisioning matrix. These resource provisioning matrices are further used by an independent authority to predict future required resources using artificial neural network. Independent authority also checks and verifies resource usage bill computed by cloud service provider using resource provisioning matrices. It provides cost computation reliability for mobile customers in mobile cloud environment. Proposed model is implemented on Hadoop using three different applications. Results indicate that proposed model provides better mobile cloud resources utilization as well as maintains quality of service for mobile customer. Proposed model increases battery life of mobile device and decreases data usage cost for mobile customer.     

云计算下基于CRP算法的资源提供策略

云计算资源管理系统是用于接收来自云计算用户的资源请求,并且把特定的资源封装为服务提供给资源请求者。在云计算环境下,如何为资源请求者选择合适的资源是一个值得研究的课题。文中通过对云计算下现有的资源提供策略的分析,同时根据不同云提供者提供的计算资源的成本不同的特点,综合考虑资源的计算能力、可靠性和单位成本三点因素,提出了云计算下基于CRP算法的资源提供策略。这种资源提供策略既能提供满足用户资源请求的服务,也能降低云服务提供者的运营成本,从而获得更大收益。     

无线多媒体通信网适应带宽配置在线优化算法

基于强化学习的方法,提出一种无线多媒体通信网适应带宽配置在线优化算法,在满足多类业务不同QoS(quality of service)要求的同时,提高网络资源的利用率.建立事件驱动的随机切换分析模型,将无线多媒体通信网中的适应带宽配置问题转化为带约束的连续时间Markov决策问题.利用此模型的动态结构特性,结合在线学习估计梯度与随机逼近改进策略,提出适应带宽配置在线优化算法.该算法不依赖于系统参数,如呼叫到达率、呼叫持续时间等,自适应性强,计算量小,能够收敛到全局最优,适用于复杂应用环境中无线多媒体通信网适应带宽配置的在线优化.仿真实验结果验证了算法的有效性.     

基于改进量子遗传算法的云计算资源调度

针对云计算环境下资源的高效调度问题,当前研究较少关注云服务提供商的服务成本,为此,以云服务提供商降低最小服务成本为目的,提出了改进量子遗传算法的云资源调度算法。由于采用二进制量子位表示的染色体无法描述资源调度矩阵,该算法将量子位的二进制编码转换为实数编码,并使用旋转策略和变异算子保证算法的收敛性。通过仿真实验平台将此算法与遗传算法和粒子群算法进行比较分析,在种群迭代次数为100的情况下,分别取种群数为1和10,实验结果表明该算法能取得更小的最小服务成本。     

Efficient resource allocation for optimizing objectives of cloud users, IaaS provider and SaaS provider in cloud environment

The cloud architecture is usually composed of several XaaS layers—including Software as a Service (SaaS), Platform as a Service (PaaS) and Infrastructure as a Service (IaaS). The paper studies efficient resource allocation to optimize objectives of cloud users, IaaS provider and SaaS provider in cloud computing. The paper proposes the composition of different layers in the cloud, such as IaaS and SaaS, and its joint optimization for efficient resource allocation. The efficient resource allocation optimization problem is conducted by subproblems. The proposed cloud resource allocation optimization algorithm is achieved through an iterative algorithm. The experiments are conducted to compare the performance of proposed joint optimization algorithm for efficient resource allocation with other related works.     

A delay-based dynamic scheduling algorithm for bag-of-task workflows with stochastic task execution times in clouds

Bag-of-Tasks (BoT) workflows are widespread in many big data analysis fields. However, there are very few cloud resource provisioning and scheduling algorithms tailored for BoT workflows. Furthermore, existing algorithms fail to consider the stochastic task execution times of BoT workflows which leads to deadline violations and increased resource renting costs. In this paper, we propose a dynamic cloud resource provisioning and scheduling algorithm which aims to fulfill the workflow deadline by using the sum of task execution time expectation and standard deviation to estimate real task execution times. A bag-based delay scheduling strategy and a single-type based virtual machine interval renting method are presented to decrease the resource renting cost. The proposed algorithm is evaluated using a cloud simulator ElasticSim which is extended from CloudSim. The results show that the dynamic algorithm decreases the resource renting cost while guaranteeing the workflow deadline compared to the existing algorithms.     

Extensions to P2MP RSVP-TE for VPN-specific state provisioning with fair resource sharing

Among the resource provisioning algorithms for the hose-based Virtual Private Network (VPN) Quality of Service (QoS), VPN-specific state provisioning allows the service provider to obtain highest resource multiplexing gains. In this paper, we show that the existing resource reservation protocols proposed for the Internet are not appropriate for the VPN-specific state provisioning. Furthermore, since the VPN-specific state provisioning makes the reserved resources to be randomly shared by the sites belonging to the same VPN, a site generating heavy traffic may unfairly dominate the resources reserved for the VPN. We propose extensions to an existing resource reservation protocol proposed for the Internet, i.e., P2MP RSVP-TE (Point-to-Multipoint Resource Reservation Protocol-Traffic Engineering), for the resource reservation of VPN-specific state provisioning. The proposed extensions also enable the fair usage of reserved resources among the users of a VPN that is provisioned by the VPN-specific state. Through simulation experiments, the effects of deploying a fair usage mechanism into the resource reservation of VPN-specific state provisioning is presented.     

云环境下基于SLA的优化资源分配研究

针对云计算环境下如何高效分配资源,实现资源供应者利润最大化这一难题,提出了一种基于服务级别协议（SLA）的动态云资源分配策略。该策略通过将SLA中的计算力、网络带宽、数据存储等属性作为优化参数,构造了一种服务请求与资源的映射模型,同时设计相应的效用函数,并结合改进的与模拟退火算法相融合的混合粒子群算法（SA-PSO）,实现云环境下的优化资源分配。实验分析结果表明,基于SLA参数的SA-PSO算法具有更好的全局最优值,在给定虚拟资源相同情况下,调用该算法完成用户任务实现的利润更高。