云计算中基于Shapley值改进遗传算法的虚拟机调度模型

云计算系统具有服务器规模大、用户范围广的特点,但同时也消耗了大量的能源,导致云供应商的高运营成本和高碳排放等问题。云计算高度虚拟化,如何分配和管理其虚拟资源,从而保证高效的物理资源利用和能耗控制,是一个多参数博弈过程,同时也是该领域的一个研究热点。提出了一种虚拟机调度模型及基于Shapley 值的遗传算法（SV-GA）,可通过经济学概念Shapley 值计算出参与工作的物理机贡献值,并通过该贡献值修正遗传算法中变异步骤的概率参数,从而完成虚拟机调度的任务。实验结果表明,与Max-Min、LrMmt及DE算法相比,SV-GA在虚拟机调度过程中的迁移时间、次数、SLA违背率、能耗等多参数博弈中具有优异的表现。     

基于布谷鸟搜索的虚拟机放置算法

针对虚拟机放置问题,引入了布谷鸟搜索算法。首先,将虚拟机放置方案映射为鸟巢,并按照适应度高低将其分成顶巢和底巢。其次,通过扰动函数对底巢和顶巢进行扰动。最后,通过选择、迭代得到最佳放置方案。该算法可用于云数据中心的物理机整合,使放置物理机数量最小化。通过Cloudsim进行仿真,仿真结果表明,比起重排序分组遗传算法、分组遗传算法、改进的最小加载和改进的降序首次适应算法,提出的方法不仅避免了局部最优,而且具有更高的性能优势。     

Data center traffic scheduling strategy based on Fibonacci tree optimization algorithm

To improve traffic scheduling capabilities in network provider data centers,both network structure and network traffic flow were considered at the same time.The analysis prediction and online scheduling mechanism was proposed in data center based on software defined networking (SDN).Aiming at the multi-dimensional,multi-constrained and multi-modal problems of traffic flow scheduling in data centers,the traffic flow scheduling strategy based on Fibonacci tree optimization (FTO) algorithm was proposed.FTO algorithm was embedded into two stages of analysis prediction and online scheduling,took it advantage of global local alternating and multi-model optimization characteristics,the optimal solution and suboptimal solutions of traffic scheduling had been got at one time.The emulator result shows that,the FTO traffic scheduling strategy can schedule traffic in data centers reasonably,which improves the load balancing capability of network providers' data centers effectively.     

基于粒子群优化算法的数据中心网络流量调度策略

为解决当前数据中心网络存在链路负载不均衡及带宽资源浪费问题,提出了一种基于粒子群优化算法的流量调度策略.该策略结合软件定义网络控制器可获取全局网络拓扑信息的特性,依据当前链路带宽资源状况及网络流量的带宽需求建立目标函数.首先,根据流的源地址和目的地址找出最短路径集,通过定义粒子聚合度判断算法是否有陷入局部最优的趋势;然...     

A prediction‐based and power‐aware virtual machine allocation algorithm in three‐tier cloud data centers

With the increasing popularity of cloud computing services, the more number of cloud data centers are constructed over the globe. This makes the power consumption of cloud data center elements as a big challenge. Hereby, several software and hardware approaches have been proposed to handle this issue. However, this problem has not been optimally solved yet. In this paper, we propose an online cloud resource management with live migration of virtual machines (VMs) to reduce power consumption. To do so, a prediction‐based and power‐aware virtual machine allocation algorithm is proposed. Also, we present a three‐tier framework for energy‐efficient resource management in cloud data centers. Experimental results indicate that the proposed solution reduces the power consumption; at the same time, service‐level agreement violation (SLAV) is also improved.