Optimized task scheduling and resource allocation on cloud computing environment using improved differential evolution algorithm

Purpose

The objective of this study is to optimize task scheduling and resource allocation using an improved differential evolution algorithm (IDEA) based on the proposed cost and time models on cloud computing environment.

Methods

The proposed IDEA combines the Taguchi method and a differential evolution algorithm (DEA). The DEA has a powerful global exploration capability on macro-space and uses fewer control parameters. The systematic reasoning ability of the Taguchi method is used to exploit the better individuals on micro-space to be potential offspring. Therefore, the proposed IDEA is well enhanced and balanced on exploration and exploitation. The proposed cost model includes the processing and receiving cost. In addition, the time model incorporates receiving, processing, and waiting time. The multi-objective optimization approach, which is the non-dominated sorting technique, not with normalized single-objective method, is applied to find the Pareto front of total cost and makespan.

Results

In the five-task five-resource problem, the mean coverage ratios C(IDEA, DEA) of 0.368 and C(IDEA, NSGA-II) of 0.3 are superior to the ratios C(DEA, IDEA) of 0.249 and C(NSGA-II, IDEA) of 0.288, respectively. In the ten-task ten-resource problem, the mean coverage ratios C(IDEA, DEA) of 0.506 and C(IDEA, NSGA-II) of 0.701 are superior to the ratios C(DEA, IDEA) of 0.286 and C(NSGA-II, IDEA) of 0.052, respectively. Wilcoxon matched-pairs signed-rank test confirms there is a significant difference between IDEA and the other methods. In summary, the above experimental results confirm that the IDEA outperforms both the DEA and NSGA-II in finding the better Pareto-optimal solutions.

Conclusions

In the study, the IDEA shows its effectiveness to optimize task scheduling and resource allocation compared with both the DEA and the NSGA-II. Moreover, for decision makers, the Gantt charts of task scheduling in terms of having smaller makespan, cost, and both can be selected to make their decision when conflicting objectives are present.     

基于改进蚁群算法的云计算资源分配策略研究

在实际的项目中会发现蚁群算法直接应用于云计算资源分配时经常会出现负载失衡的情况,导致资源利用率不高,同时导致任务完成时间太长,算法迭代次数过大。这种情况不仅会大大地降低云计算系统的效率,还会造成系统不稳定。因此针对蚁群算法进行了一系列改进,具体包括：引入伪随机比例规则,进行全局信息素强化,引入了交叉变异操作,将蚁群算法与遗传算法相融合。然后进行了MATLAB仿真实验,实验结果表明：改进算法的任务完成时间更短,算法迭代次数更少,负载均衡效果更好。由此可以得出结论：对蚁群算法的改进是有效的。     

云计算中虚拟机资源分配算法

为了解决云计算中虚拟机部署预留方案浪费大量资源和单目标部署方案不够全面问题,提出了一种基于组的多目标遗传算法虚拟机资源分配算法.该算法分成组编码和资源编码,资源编码根据虚拟机历史资源需求进行整合编码,通过改进的交叉和变异操作,将物理机器个数和虚拟机占用物理机器资源整合.实验结果表明,该算法有效减少了物理机器个数使用和提高了物理机器资源使用率,达到了节能目的.     

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.     

云计算环境下的混沌萤火虫的资源负载均衡算法

负载均衡问题是当前云计算研究的重要问题。由于云计算中的负载均衡存在效率低、准确性不高以及资源需求动态变化等问题,建立了云计算环境下的负载均衡模型,通过在发送者策略中引入混沌算法和在接收者策略中引入萤火虫算法,提高了目标节点的最优化选择以及转移任务量的准确性。仿真实验表明,改进后的资源负载算法能够有效地避免负载处理的不均衡,提高系统整体处理能力。     

无线传感网络任务分配的能效性控制策略

无线传感网络包含大量密集分布传感节点,各节点测量产生大量数据给传输、存储、管理和分析带来困难,无线传感网络能源不可更换性限制了网络寿命.本文提出基于熵理论和欧式距离的网络能耗评价指标,采用对等(peer-to-peer,简称P2P)计算方法,利用基于蚁群智能的能效性优化任务分配控制策略,针对中心节点工作状态、传输能耗和网络寿命实现动态实时任务控制分配,完成多中心节点并行计算,提高网络工作效率,节约能耗.实验表明基于蚁群智能的能效性任务分配控制策略能实时有效地缩短无线传感网络计算时间,减少网络能耗,提高网络寿命.     

移动边缘计算环境下的动态资源分配策略

在通讯设备爆炸式增长的时代,移动边缘计算作为5G通讯技术的核心技术之一,对其进行合理的资源分配显得尤为重要。移动边缘计算的思想是把云计算中心下沉到基站部署(边缘云),使云计算中心更加靠近用户,以快速解决计算资源分配问题。但是,相对于大型的云计算中心,边缘云的计算资源有限,传统的虚拟机分配方式不足以灵活应对边缘云的计算资源分配问题。为解决此问题,提出一种根据用户综合需求变化的动态计算资源和频谱分配算法(DRFAA),采用"分治"策略,并将资源模拟成"流体"资源进行分配,以寻求较大的吞吐量和较低的传输时延。实验仿真结果显示,动态计算资源和频谱分配算法可以有效地降低用户与边缘云之间的传输时延,也可以提高边缘云的吞吐量。     

云计算环境下基于模板的任务调度策略与算法

针对云计算任务调度,提出了一种基于模板的任务调度（Template-based Task Scheduling,TTS）策略。该策略充分考虑了通信开销,在对任务分配进行预处理的基础上实现任务调度,主要分为两步：针对一个任务集合,采用可分任务调度求解子任务大小的方法,求出各个处理机应该分担的任务量模板;根据求出的模板,采用合理的调度算法对任务进行调度,从而得到较优的调度结果。在TTS策略下,对传统贪心算法加以改进,最终提出基于模板的任务调度贪心算法（Template-based Task Scheduling Greedy Algorithm,TTSGdA）。与Min-min算法和遗传算法的对比实验结果表明,TTSGdA能够有效减少任务集合完成时间。     

云环境下基于偏好的资源公平分配策略

资源分配策略是云计算领域的一个重要研究热点,其主要目标是同时考虑云用户和云提供商双方的利益,有效满足系统用户和任务的公平性,同时尽可能达到系统资源的充分利用。考虑到云环境中的用户需求各异,每个用户的任务请求数量不同,各个任务的资源需求也不同,设计了一种基于偏好的公平分配策略FABP,并给出了用户优先级和任务优先级的定义。实验分析表明,该算法不仅能缩短平均任务调度时间,而且还可以保证任务调度过程中用户和任务的公平性,实现综合资源利用率的最大化。     

无线传感器网络中一种能量高效的分布式分簇算法

提出了一种适用于无线传感器网络的能量高效的分布式分簇算法（ＥＥＤＣ）,该算法使具有较高剩余能量及距离基站较近的节点有更大的机会成为簇头．理论分析表明该算法通信开销较小,而且有效地均衡了节点的能量消耗．为了确保ＥＥＤＣ 的正确性、完整性和可靠性,利用形式化方法———着色网对其关键属性进行建模和分析．仿真结果表明,ＥＥＤＣ 有效地延长了网络生命周期,提高了网络的能耗效率．     

一种无线传感器网络非均匀分布节点定位算法

提出了一种基于加权处理的无线传感器网络非均匀分布节点定位算法-W-DV-Hop算法.算法对所有锚节点的平均跳距进行加权处理作为网络平均跳距,使网络平均每跳距离的估计更加准确,从而降低用锚节点的平均跳距作为网络每跳距离对定位精度的影响.仿真结果表明:在同等条件下,新算法相比DV-Hop算法能有效提高节点定位精度,且能延长节点寿命.     

FRP: a fast resource placement algorithm in distributed cloud computing platform

We consider a large‐scale online service system of placing resources geographically distributed over multiple regional cloud data centers. Service providers need to place the resources in these regions so as to maximize profit, accounting for demand granting revenues minus resource placement costs. The challenge is how to optimally place these resources to fulfill varying demands (e.g., multidimensional and stochastic demands) among these cloud data centers. Considering demand stochasticity will significantly increase time complexity of resource placement algorithm, resulting in inefficiency when handling a large number of resources. We propose a fast resource placement algorithm (FRP) to obtain the maximum resource revenue from distributed cloud systems. Experiments show that in scenarios with general settings, FRP can achieve up to 99.2% revenue of existed best solution while reducing execution time by two orders of magnitude. Therefore, FRP is an effective supplement to existing algorithms under time‐tense scheduling scenarios with a large number of resources. Copyright © 2015 John Wiley & Sons, Ltd.     

Cooperative distributed target tracking algorithm in mobile wireless sensor networks

The paper proposes a cooperative distributed target tracking algorithm in mobile wireless sensor networks.There are two main components in the algorithm:distributed sensor-target assignment and sensor motion control.In the key idea of the sensor-target assignment,sensors are considered as autonomous agents and the defined objective function of each sensor concentrates on two fundamental factors:the tracking accuracy and the tracking cost.Compared with the centralized algorithm and the noncooperative distrib...     

无线传感器网络中基于MDS-MCC问题的启发式算法研究

在保证覆盖和连通性的情况下,通过节能技术延长网络寿命是无线传感器网络的核心研究之一。基于MDS-MCC问题的启发式算法利用睡眠机制实现节能,该算法使用以路径长度为优先考虑因子的greedy策略选择最大不相交集合,但是使用该策略不能得到最大不相交集合个数,因此本文针对该策略提出了以覆盖为主要考虑因子的基于DFS和BFS结合的搜索算法(DBFS)。本文建立的模型是以不相交集合个数为网络寿命的衡量标准的,不相交集合个数越多表明网络寿命越长,仿真实验结果证明,从不相交集合的个数(也就是网络寿命)以及实验结果的稳定性来看,DBFS算法要优于greedy策略。     

An SLA-based cloud computing that facilitates resource allocation in the distributed data centers of a cloud provider

The number of cloud service users has increased worldwide, and cloud service providers have been deploying and operating data centers to serve the globally distributed cloud users. The resource capacity of a data center is limited, so distributing the load to global data centers will be effective in providing stable services. Another issue in cloud computing is the need for providers to guarantee the service level agreements (SLAs) established with consumers. Whereas various load balancing algorithms have been developed, it is necessary to avoid SLA violations (e.g., service response time) when a cloud provider allocates the load to data centers geographically distributed across the world. Considering load balancing and guaranteed SLA, therefore, this paper proposes an SLA-based cloud computing framework to facilitate resource allocation that takes into account the workload and geographical location of distributed data centers. The contributions of this paper include: (1) the design of a cloud computing framework that includes an automated SLA negotiation mechanism and a workload- and location-aware resource allocation scheme (WLARA), and (2) the implementation of an agent-based cloud testbed of the proposed framework. Using the testbed, experiments were conducted to compare the proposed schemes with related approaches. Empirical results show that the proposed WLARA performs better than other related approaches (e.g., round robin, greedy, and manual allocation) in terms of SLA violations and the provider’s profits. We also show that using the automated SLA negotiation mechanism supports providers in earning higher profits.     

基于深度Q学习的室内无线网络资源分配算法

针对室内无线网络中的能量消耗过大问题,提出了一种基于深度Q学习的家庭基站发射功率分配算法.首先构造深度学习网络(DLN),优化室内无线网络的能量效率;然后将能量消耗指数作为奖罚值,利用批量梯度下降法不断地训练DLN的权值.最后仿真结果表明,所提出的算法可以动态调整发射功率,在收敛速度和能量消耗优化方面明显优于Q学习算法...     

一种混合无线传感器网络内覆盖洞修补的分布式启发算法

首先对最小化最大移动开销移动传感器分布式算法设计进行了分析, 并指出在分布式条件下难以对此类算法中的输出分派移动传感器的最大开销进行限制, 随后提出了一种分布式启发算法。该算法将移动传感器和覆盖洞视为节点, 在节点和节点的邻居间通过有限数量消息实现匹配。仿真结果显示, 算法可实现最高达到85%的覆盖洞修补率以及较低的移动传感器最大移动开销, 使其更能适用于实际无线传感器网络环境。     

一种基于约束策略的无线传感器网络定位算法*

节点定位技术是无线传感器网络的关键支撑技术之一,对于无线传感器网络的基本理论方法和应用研究都具有重要意义。在深入研究分析距离无关定位算法的基础上,提出了基于约束策略的无线传感器网络定位算法。该算法无须测距,采用跳数估计节点间距离,并针对未知节点到锚节点距离计算中的不足,对锚节点的平均每跳距离作了修正;在估计未知节点坐标时,根据该未知节点通信范围内的锚节点对其所在位置进行约束。仿真结果表明,该算法具有较好的性能,比已有算法的定位精度有所提高。     

基于元区间的云计算基础设施服务的资源分配算法研究

针对云计算中基础设施服务资源分配问题,提出了一种最佳分配决策算法。该算法通过估计待选元区间的资源配额参数,选择一个最小的满足用户应用要求的元区间,提高了基础设施服务资源的利用率。首先给出了基于元区间的基础设施服务模型,其次给出了云用户应用以及元区间资源之间的适应模型,最后提出了元区间决策算法并对该算法进行了系统地评价,该算法取得良好的效果。     

云环境下公平性优化的资源分配方法

针对云数据中心资源分配不均、效率不高、资源错位等问题,为了满足不同用户的需求,达到多种资源分配的公平性,实现资源的高效利用,提出了全局优势资源公平（GDRF）分配算法。GDRF算法采用多轮分配方式,即先通过用户已分配资源量确定分配资格,每轮再通过全局优势资源共享比和全局优势资源权重来确定具体的分配用户,分配过程充分考虑了资源的匹配情况,采用了max-min fairness思想的渐进填充方式,并且将多资源分配公平性统一度量模型运用到了算法中。实验基于一个Google集群数据模型与基于占优资源的多资源联合公平分配算法作了比较。实验结果表明,GDRF算法分配的虚拟机总量提高了12%,资源总利用率提高了0.5个百分点,公平评估值提高了约15%,并且该算法的资源组合分配的适应度较高,使得用户需求和供给更匹配。