基于动态规划的虚拟机放置策略

在IaaS云环境中,资源的分配管理关键取决于如何放置虚拟机,不当的放置策略可造成资源的损耗以及更多的能耗开销。为了降低整个数据中心的资源损耗和能耗开销,建立一个多目标优化的问题模型,并提出了一种基于动态规划思想的虚拟机放置策略。策略将放置问题转化为多阶段决策的背包问题,利用动态规划的思想把背包问题划分成一系列规模更小的子问题,通过求解子问题的最优解得到原问题的最优解。仿真实验表明,该策略能大大降低数据中心的能耗,并减少资源损耗。     

一种新的蚁群算法优化的虚拟机放置策略

提出了一种新的蚁群算法优化的虚拟机放置策略ACA-VMP (Ant Colony Algorithm based virtual machine placement);ACA-VMP以云数据中心的总体能量消耗降低、服务质量最佳及减少虚拟机迁移次数为目标函数;根据蚁群优化算法,ACA-VMP采用了全局最优解和局部最优解信息素强度更新规则;全局最优解经过多次迭代后,蚂蚁路径的多次寻优,保证这个虚拟机放置优化策略的完成;局部信息素强度参数更新可以补充蚂蚁其他局部最优路径的寻找,这样也可以使得ACA-VMP虚拟机放置优化算法更快的接近全局最优解;仿真结果表明:ACA-VMP策略使得云数据中心的各类性能指标都可以改善,该实验结果对于其他企业构造节能云数据中心有很好的参考价值.     

基于混合群智能的节能虚拟机整合方法

数据中心的虚拟机（virtual machine,VM）整合技术是当今云计算领域的一个研究热点.要在保证服务质量（QoS）的前提下尽可能地降低云数据中心的服务器能耗,本质上是一个多目标优化的NP难问题.为了更好地解决该问题,面向异构服务器云环境提出了一种基于差分进化与粒子群优化的混合群智能节能虚拟机整合方法（HSI-VMC）.该方法包括基于峰值效能比的静态阈值超载服务器检测策略（PEBST）、基于迁移价值比的待迁移虚拟机选择策略（MRB）、目标服务器选择策略、混合离散化启发式差分进化粒子群优化虚拟机放置算法（HDH-DEPSO）以及基于负载均值的欠载服务器处理策略（AVG）.其中,PEBST,MRB,AVG策略的结合能够根据服务器的峰值效能比和CPU的负载均值检测出超载和欠载服务器,并选出合适的虚拟机进行迁移,降低负载波动引起的服务水平协议违约率（SLAV）和虚拟机迁移的次数;HDH-DEPSO算法结合DE和PSO的优点,能够搜索出更优的虚拟机放置方案,使服务器尽可能地保持在峰值效能比下运行,降低服务器的能耗开销.基于真实云环境数据集（PlanetLab/Mix/Gan）的一系列实验结果表明：HSI-VMC方法与当前主流的几种节能虚拟机整合方法相比,能够更好地兼顾多个QoS指标,并有效地降低云数据中心的服务器能耗开销.     

云环境下基于模糊隶属度的虚拟机放置算法

虚拟机放置问题是云数据中心资源调度的核心问题之一,它对数据中心的性能、资源利用率和能耗有着重要的影响。针对此问题,以降低数据中心能耗、改善资源利用率和保证服务质量(QoS)为优化目标,借助模糊聚类的思想提出了一种基于模糊隶属度的虚拟机放置算法。首先,结合物理主机过载概率和虚拟机与物理主机之间的相适性放置关系,提出了新的距离度量方法;然后,根据模糊隶属度函数计算得出虚拟机与物理主机之间的相适性模糊隶属度矩阵;最后,借助能耗感知机制,在模糊隶属度矩阵中进行局部搜索从而获得迁移虚拟机的最优放置方案。仿真实验结果表明,提出的算法在降低云数据中心能耗、改善资源利用率和保证QoS方面表现比较优异。     

Towards an adaptive human-centric computing resource management framework based on resource prediction and multi-objective genetic algorithm

The complexity, scale and dynamic of data source in the human-centric computing bring great challenges to maintainers. It is problem to be solved that how to reduce manual intervention in large scale human-centric computing, such as cloud computing resource management so that system can automatically manage according to configuration strategies. To address the problem, a resource management framework based on resource prediction and multi-objective optimization genetic algorithm resource allocation (RPMGA-RMF) was proposed. It searches for optimal load cluster as training sample based on load similarity. The neural network (NN) algorithm was used to predict resource load. Meanwhile, the model also built virtual machine migration request in accordance with obtained predicted load value. The multi-objective genetic algorithm (GA) based on hybrid group encoding algorithm was introduced for virtual machine (VM) resource management, so as to provide optimal VM migration strategy, thus achieving adaptive optimization configuration management of resource. Experimental resource based on CloudSim platform shows that the RPMGA-RMF can decrease VM migration times while reduce physical node simultaneously. The system energy consumption can be reduced and load balancing can be achieved either.     

Application type based resource allocation strategy in cloud environment

Unreasonable resource allocation may shorten the service life of physical servers and affect the stability of the cloud data center. To solve this issue, a virtual machine (VM) allocation and placement strategy based on the types of applications is proposed. According to the strategy, appropriate VM is allocated based on the type of application. And the VM is placed on the server that the available resources is sufficient enough to support the application. Meanwhile, the load balance of the server is also considered when the VM is placed. Simulations on Cloudsim platform show that the performance of load balance of the VM placement strategy proposed is much better than that of the traditional VM placement strategy. And extensive experiments on cloudstack show that the VM placement strategy proposed is much more efficient than the traditional VM placement strategy in execution.     

An efficient energy-aware method for virtual machine placement in cloud data centers using the cultural algorithm

Excessive consumption of energy in cloud data centers whose number is increasing day by day has led to substantial problems. Hence, offering efficient schemes for virtual machine (VM) placement to decrease energy consumption in cloud computing environments has become a significant research field in recent years. In this paper, with the goal of reducing energy consumption in cloud data centers, we present a VM placement method using the cultural algorithm. In the proposed algorithm called balance-based cultural algorithm for virtual machine placement (BCAVMP), a new fitness function is introduced to evaluate VM allocation solutions. In this function, by using the sum of balance vector lengths for each VM placement, balanced utilization of resources is considered. Also, by applying the amount of energy usage in the fitness function, solutions with lower energy consumption are intended. The performance of the proposed method is evaluated using CloudSim simulator. The simulation results indicate that by appropriate VM assignment and resource wastage reduction, energy consumption in cloud data centers can be decreased.

     

基于自适应过载阈值选择的虚拟机动态整合方法

针对云环境下动态工作负载的不确定性,提出了基于自适应过载阈值选择的虚拟机动态整合方法。为了权衡数据中心能源有效性与服务质量间的关系,将自适应过载阈值的选择问题建模为马尔可夫决策过程,计算过载阈值的最优选择策略,并根据系统能效和服务质量调整阈值。通过过载阈值检测过载物理主机,然后根据最小迁移时间原则以及最小能耗增加放置原则确定虚拟机的迁移策略,最后切换轻负载物理主机至休眠状态完成虚拟机整合。仿真实验结果表明,所提出的方法在减少虚拟机迁移次数方面效果显著,在节约数据中心能源开销与保证服务质量方面表现良好,在能源的有效性与云服务质量二者之间取得了比较理想的平衡。     

基于三支决策的虚拟机节能迁移策略

虚拟机迁移技术作为云计算中降低数据中心能耗的重要手段被广泛应用。结合三支决策的分、治、效模型提出一种基于三支决策的虚拟机迁移调度策略（TWD-VMM）。首先,通过建立层次阈值树搜索所有可能取到的阈值,由此以数据中心能耗为优化目标得到总能耗最低的一对阈值,从而实现三分区域,即高负载区域、中负载区域和低负载区域。其次,针对不同负载的主机采取不同的迁移策略：对于高负载主机,以主机预迁出后的多维资源均衡度和主机负载下降幅度为目标;对于低负载主机,主要考虑主机预放置后的多维资源均衡度;对于中等负载主机,如果迁移过来的虚拟机依旧满足中负载特性,则可以接受迁入。实验采用CloudSim模拟器进行,将TWD-VMM算法分别与基于阈值调度算法（TVMS）、基于虚拟机迁移节能调度算法（EEVS）、云计算中心节能调度算法（REVMS）算法在主机负载、主机多维资源利用均衡度、数据中心总能耗等方面进行比较,结果表明TWD-VMM算法在提高主机资源利用率、均衡主机负载等方面有明显效果,且能耗平均降低了27%。     

面向移动云计算的自适应虚拟机调度算法

随着移动云计算的快速发展和应用普及,如何对移动云中心资源进行有效管理同时又降低能耗、确保资源高可用是目前移动云计算数据中心的热点问题之一.本文从CPU、内存、网络带宽和磁盘四个维度,建立了基于多目标优化的虚拟机调度模型VMSM-EUN(Virtual Machine Scheduling Model based on Energy consumption,Utility and minimum Number of servers),将最小化数据中心能耗、最大化数据中心效用以及最小化服务器数量作为调度目标.设计了基于改进粒子群的自适应参数调整的虚拟机调度算法VMSA-IPSO(Virtual Machine Scheduling Algorithm based on Improved Particle Swarm Optimization)来求解该模型.最后通过仿真实验验证了本文提出的调度算法的可行性与有效性.对比实验结果表明,本文设计的基于改进粒子群的自适应虚拟机调度算法在进行虚拟机调度时,能在降低能耗的同时提高数据中心效用.     

基于Orbital Shrinking的数据中心虚拟机最优放置算法

摘要：虚拟机放置技术能够控制智能电网数据中心物理服务器的资源使用,将有效提升资源使用效率。虚拟机放置策略的思路主要基于时间、空间、计算资源和能耗的综合均衡,其主要面临的瓶颈包括鲁棒性和灵活性的平衡矛盾,以及有限资源的非均衡分配问题。根据当前电力数据中心结构复杂和资源利用率低的问题,本文提出一种基于Orbital Shrinking的数据中心虚拟机最优放置算法,首先研究虚拟机放置的数据中心适用性问题,有效地从多维目标优化和边界动态约束这2方面分析数据中心的资源状态。基于Orbital Shrinking模型,建立计算资源、时空状态和能耗条件的多维背包模型,实现虚拟机放置策略的整体平衡。通过实验仿真表明,新算法能够有效提升数据中心服务器的计算资源利用效率9.8%,降低数据处理时延10.3 s。     

Recent advancement in VM task allocation system for cloud computing: review from 2015 to2021

Cloud computing is new technology that has considerably changed human life at different aspect over the last decade. Especially after the COVID-19 pandemic, almost all life activity shifted into cloud base. Cloud computing is a utility where different hardware and software resources are accessed on pay per user ground base. Most of these resources are available in virtualized form and virtual machine (VM) is one of the main elements of visualization.VM used in data center for distribution of resource and application according to benefactor demand. Cloud data center faces different issue in respect of performance and efficiency for improvement of these issues different approaches are used. Virtual machine play important role for improvement of data center performance therefore different approach are used for improvement of virtual machine efficiency (i-e) load balancing of resource and task. For the improvement of this section different parameter of VM improve like makespan, quality of service, energy, data accuracy and network utilization. Improvement of different parameter in VM directly improve the performance of cloud computing. Therefore, we conducting this review paper that we can discuss about various improvements that took place in VM from 2015 to 20,201. This review paper also contain information about various parameter of cloud computing and final section of paper present the role of machine learning algorithm in VM as well load balancing approach along with the future direction of VM in cloud data center.

     

Virtual machine selection and placement for dynamic consolidation in Cloud computing environment

Dynamic consolidation of virtual machines (VMs) in a data center is an effective way to reduce the energy consumption and improve physical resource utilization. Determining which VMs should be migrated from an overloaded host directly influences the VM migration time and increases energy consumption for the whole data center, and can cause the service level of agreement (SLA), delivered by providers and users, to be violated. So when designing a VM selection policy, we not only consider CPU utilization, but also define a variable that represents the degree of resource satisfaction to select the VMs. In addition, we propose a novel VM placement policy that prefers placing a migratable VM on a host that has the minimum correlation coefficient. The bigger correlation coefficient a host has, the greater the influence will be on VMs located on that host after the migration. Using CloudSim, we run simulations whose results let draw us to conclude that the policies we propose in this paper perform better than existing policies in terms of energy consumption, VM migration time, and SLA violation percentage.     

云数据中心基于贪心算法的虚拟机迁移策略

为了节省云数据中心的能量消耗,提出了几种基于贪心算法的虚拟机（VM）迁移策略。这些策略将虚拟机迁移过程划分为物理主机状态检测、虚拟机选择和虚拟机放置三个步骤,并分别在虚拟机选择和虚拟机放置步骤中采用贪心算法予以优化。提出的三种迁移策略分别为：最小主机使用效率选择且最大主机使用效率放置算法MinMax_Host_Utilization、最大主机能量使用选择且最小主机能量使用放置算法MaxMin_Host_Power_Usage、最小主机计算能力选择且最大主机计算能力放置算法MinMax_Host_MIPS。针对物理主机处理器使用效率、物理主机能量消耗、物理主机处理器计算能力等指标设置最高或者最低的阈值,参考贪心算法的原理,在指标上超过或者低于这些阈值范围的虚拟机都将进行迁移。利用CloudSim作为云数据中心仿真环境的测试结果表明,基于贪心算法的迁移策略与CloudSim中已存在的静态阈值迁移策略和绝对中位差迁移策略比较起来,总体能量消耗少15%,虚拟机迁移次数少60%,平均SLA违规率低5%。     

云计算中高能效的虚拟资源分配策略

社会对云计算需求的不断扩大需要构建规模巨大的数据中心,如何高能效地运行数据中心是一个急待解决的问题。传统的虚拟资源分配策略没有充分地考虑如何有效地降低数据中心的能耗和策略生成的时间复杂度,提出了一种高能效的虚拟资源分配策略（EEVRAS）,通过将云计算中的虚拟资源分配问题模型化为一个路径构建的问题,同时改进精华策略的蚂蚁系统（EAS）来进行资源分配方案的优化。策略生成的时间复杂度较低。仿真结果表明相对传统的虚拟资源分配策略,在服务器性能指标约束下,EEVRAS策略能够使用较少的服务器构建虚拟集群,从而有效地降低数据中心的能耗。     

Adaptive Markov-based approach for dynamic virtual machine consolidation in cloud data centers with quality-of-service constraints

Dynamic virtual machine (VM) consolidation is one of the emerging technologies that has been considered for low-cost computing in cloud data centers. Quality-of-service (QoS) assurance is one of the challenging issues in the VM consolidation problem since it is directly affected by the increase of resource utilization due to the consolidations. In this paper, we take advantage of Markov chain models to propose a novel approach for VM consolidation that can be used to explicitly set a desired level of QoS constraint in a data center to ensure the QoS goals while improving system utilization. For this purpose, an energy-efficient and QoS-aware best fit decreasing algorithm for VM placement is proposed, which considers QoS objective when determining the location of a migrating VM. This algorithm employs an online transition matrix estimator method to deal with the nonstationary nature of real workload data. We also propose new policies for detecting overloaded and underloaded hosts. The performance of our proposed algorithms is evaluated through simulations. The results show that the proposed VM consolidation algorithms in this paper outperforms the benchmark algorithms in terms of energy consumption, service-level agreement violations, and other cost factors.     

Profile-based dynamic application assignment with a repairing genetic algorithm for greener data centers

Data centers have become essential to modern society by catering to increasing number of Internet users and technologies. This results in significant challenges in terms of escalating energy consumption. Research on green initiatives that reduce energy consumption while maintaining performance levels is exigent for data centers. However, energy efficiency and resource utilization are conflicting in general. Thus, it is imperative to develop an application assignment strategy that maintains a trade-off between energy and quality of service. To address this problem, a profile-based dynamic energy management framework is presented in this paper for dynamic application assignment to virtual machines (VMs). It estimates application finishing times and addresses real-time issues in application resource provisioning. The framework implements a dynamic assignment strategy by a repairing genetic algorithm (RGA), which employs realistic profiles of applications, virtual machines and physical servers. The RGA is integrated into a three-layer energy management system incorporating VM placement to derive actual energy savings. Experiments are conducted to demonstrate the effectiveness of the dynamic approach to application management. The dynamic approach produces up to 48% better energy savings than existing application assignment approaches under investigated scenarios. It also performs better than the static application management approach with 10% higher resource utilization efficiency and lower degree of imbalance.     

容器云环境虚拟资源配置策略的优化

针对容器化云环境中数据中心能耗较高的问题，提出了一种基于最佳能耗优先（Power Full，PF）物理机选择算法的虚拟资源配置策略。首先，提出容器云虚拟资源的配置和迁移方案，发现物理机选择策略对数据中心能耗有重要影响；其次，通过研究主机利用率与容器利用率，主机利用率与虚拟机利用率，主机利用率与数据中心能耗之间的数学关系，建立容器云数据中心能耗的数学模型，定义出优化目标函数；最后，通过对物理机的能耗函数使用线性插值进行模拟，依据邻近事物相类似的特性，提出改进的最佳能耗优先物理机选择算法。仿真实验将此算法与先来先得（First Fit，FF）、最低利用率优先（Least Fit，LF）、最高利用率优先（Most Full，MF）进行比较，实验结果表明，在有规律不同物理机群的计算服务中，其能耗比FF、LF、MF分别平均降低45%、53%和49%；在有规律相同物理机群的计算服务中，其能耗比FF、LF、MF分别平均降低56%、46%和58%；在无规律不同物理机群的计算服务中，其能耗比FF、LF、MF分别平均降低32%、24%和12%。所提算法实现了对容器云虚拟资源的合理配置，且在数据中心节能方面具有优越性。     

大数据云中心虚拟机资源高效分配应用研究

为降低大数据云中心的能量消耗和实现资源的优化配置,提出一种虚拟机资源高效分配策略;提出的策略对选定的特征上具备相似性任务分组的聚类进行定义,将各组任务映射到定制化的高效虚拟机类型;其高效指的是以最低限度的资源损耗成功执行任务;虚拟机的相关参数为核数量、内存量和存储量;虚拟机分配基于日志中提取的历史数据,并以任务的使用模式为基础;提出的资源分配策略以任务的实际资源使用量为基础,实现了能源消耗的降低;实验结果表明:不同聚类任务下,提出的虚拟机资源分配策略可以大幅节约能源消耗,具有较低的平均任务拒绝次数。     

云计算中基于多目标优化的动态资源配置方法

目前,云平台的大多数动态资源分配策略只考虑如何减少激活物理节点的数量来达到节能的目的,以实现绿色计算,但这些资源再配置方案很少考虑到虚拟机放置的稳定性。针对应用负载的动态变化特征,提出一种新的面向多虚拟机分布稳定性的基于多目标优化的动态资源配置方法,结合各应用负载的当前状态和未来的预测数据,综合考虑虚拟机重新放置的开销以及新虚拟机放置状态的稳定性,并设计了面向虚拟机分布稳定性的基于多目标优化的遗传算法（MOGANS）进行求解。仿真实验结果表明,相对于面向节能和多虚拟机重分布开销的遗传算法（GA-NN）,MOGANS得到的虚拟机分布方式的稳定时间是GA-NN的10.42倍;同时,MOGANS也较好权衡了多虚拟机分布的稳定性和新旧状态转换所需的虚拟机迁移开销之间的关系。