云中截止时间动态分配的工作流调度成本优化算法

现如今,如何在满足截止时间约束的前提下降低工作流的执行成本,是云中工作流调度的主要问题之一。三步列表调度算法可以有效解决这一问题。但该算法在截止时间分配阶段只能形成静态的子截止时间。为方便用户部署工作流任务,云服务商为用户提供了的三种实例类型,其中竞价实例具有非常大的价格优势。为解决上述问题,提出了截止时间动态分配的工作流调度成本优化算法(S-DTDA)。该算法利用粒子群算法对截止时间进行动态分配,弥补了三步列表调度算法的缺陷。在虚拟机选择阶段,该算法在候选资源中增加了竞价实例,大大降低了执行成本。实验结果表明,相较于其他经典算法,该算法在实验成功率和执行成本上具有明显优势。综上所述,S-DTDA算法可以有效解决工作流调度中截止时间约束的成本优化问题。     

服务质量感知的云应用资源自适应配置

针对部署在云环境下的云应用资源配置优化问题,提出了通过感知服务质量变化自适应配置云应用资源的策略。设计了一种基于采集到的历史运行指标数据生成贝叶斯网络概率推理模型,并利用预定义应用服务质量目标（Service Level Objectives,SLO）找到资源超配或不足的虚拟设备,生成资源优化方案。在仿真环境下验证测试结果显示,开启自适应配置算法的云应用请求响应时间指标明显优于未开启的云应用。     

Resource provisioning for cloud applications: a 3-D,provident and flexible approach

The scalability feature of cloud computing attracts application service providers (ASPs) to use cloud application hosting. In cloud environments, resources can be dynamically provisioned on demand for ASPs. Autonomic resource provisioning for the purpose of preventing resources over-provisioning or under-provisioning is a widely investigated topic in cloud environments. There has been proposed a lot of resource-aware and/or service-level agreement (SLA)-aware solutions to handle this problem. However, intelligence solutions such as exploring the hidden knowledge on the Web users’ behavior are more effective in cost efficiency. Most importantly, with considering cloud service diversity, solutions should be flexible and customizable to fulfill ASPs’ requirements. Therefore, lack of a flexible resource provisioning mechanism is strongly felt. In this paper, we proposed an autonomic resource provisioning mechanism with resource-aware, SLA-aware, and user behavior-aware features, which is called three-dimensional mechanism. The proposed mechanism used radial basis function neural network in order to provide providence and flexibility features. The experimental results showed that the proposed mechanism reduces the cost while guarantees the quality of service.     

A fault‐tolerant dynamic scheduling method on hierarchical mobile edge cloud computing

Mobile edge cloud computing has been a promising computing paradigm, where mobile users could offload their application workloads to low‐latency local edge cloud resources. However, compared with remote public cloud resources, conventional local edge cloud resources are limited in computation capacity, especially when serve large number of mobile applications. To deal with this problem, we present a hierarchical edge cloud architecture to integrate the local edge clouds and public clouds so as to improve the performance and scalability of scheduling problem for mobile applications. Besides, to achieve a trade‐off between the cost and system delay, a fault‐tolerant dynamic resource scheduling method is proposed to address the scheduling problem in mobile edge cloud computing. The optimization problem could be formulated to minimize the application cost with the user‐defined deadline satisfied. Specifically, firstly, a game‐theoretic scheduling mechanism is adopted for resource provisioning and scheduling for multiprovider mobile applications. Then, a mobility‐aware dynamic scheduling strategy is presented to update the scheduling with the consideration of mobility of mobile users. Moreover, a failure recovery mechanism is proposed to deal with the uncertainties during the execution of mobile applications. Finally, experiments are designed and conducted to validate the effectiveness of our proposal. The experimental results show that our method could achieve a trade‐off between the cost and system delay.     

移动云计算中能效感知的计算卸载机制研究

移动云计算可以将任务从移动设备计算卸载至云端以增强设备计算能力,而如何实现能效计算卸载机制是当前的主要挑战。为了解决该问题,以降低移动设备能耗和应用完成时间为目标,将计算卸载问题形式化为满足任务顺序与截止时间约束的能效代价最小化问题,并提出一种动态能效感知计算卸载算法。算法由三个子算法组成：计算卸载选择、时钟频率控制及传输功率分配。实验结果表明,通过局部计算时优化调整移动设备CPU时钟频率,以及云端计算时自适应分配传输功率,新算法可以有效降低应用执行能效代价,同时确保满足约束条件,提高执行效率。     

基于云存储的多用户可搜索加密方案

云存储服务允许用户外包数据并以此来降低资源开销。针对云服务器不被完全信任的现状,文章研究如何在云环境下对数据进行安全存储和加密搜索。多用户的可搜索加密方案为用户提供了一种保密机制,使用户可以在不受信任的云存储环境下安全地共享信息。在现有的可搜索加密方案的基础上,文章提出了一种安全有效的带关键字搜索的加密方案,以及更加灵活的密钥管理机制,降低了云端数据处理的开销。     

An enhanced load balancing mechanism based on deadline control on GridSim

A Grid is a network of computational resources that may potentially span many continents. Load balancing in a Grid is a hot research issue which affects every aspect of the Grid, including service selection and task execution. Thus, it is necessary and significant to solve the load balancing problem in a Grid. In this paper, we propose a dynamic, distributed load balancing scheme for a Grid which provides deadline control for tasks. In our scenario, first, resources check their state and make a request to the Grid Broker according to the change of load state. Then, the Grid Broker assigns Gridlets between resources and scheduling for load balancing under the deadline request. We apply our load balancing strategy into a popular Grid simulation platform GridSim. Experimental results prove that our proposed load balancing mechanism can (1) reduce the makespan, (2) improve the finished rate of the Gridlet, and (3) reduce the resubmitted time.     

A cloud service selection model using improved ranked voting method

Cloud computing is an upcoming and promising solution for utility computing that provides resources on demand. As it has grown into a business model, a large number of cloud service providers exist today in the cloud market, which further is expanding exponentially. Many cloud service providers, with almost similar functionality, pose a selection problem to the cloud users. To assist the users in the best service selection, as per its requirement, a framework has been developed in which users list their quality of service (QoS) expectation, while service providers express their offerings. Experience of the existing cloud users is also taken into account in order to select the best cloud service provider. This work identifies some new QoS metrics, besides few existing ones, and defines it in a way that eases both the user and the provider to express their expectations and offers, respectively, in a quantified manner. Further, a dynamic and flexible model, using a variant of ranked voting method, is proposed that considers users' requirement and suggests the best cloud service provider. Case studies affirm the correctness and the effectiveness of the proposed model. Copyright © 2016 John Wiley & Sons, Ltd.     

基于多QoS目标的工作流任务调度算法

根据工作流任务的结构特点对其进行分区,按照任务量和通信量将总工作流截止日期和总工作流花费分为每个任务分区上的子截止日期和子花费,在考虑用户多个QoS要求及工作流任务间通信时间的基础上,提出基于信任与花费的综合效益函数,给出信任与花费权值的确定方法以及一个以综合效益最优为目标的调度算法——TCD,算法通过追求局部最优达到全局多目标优化调度。与其他算法的比较表明,该算法服务拒绝率最多可降低15%,能较好地满足用户多QoS要求。     

Utility-based RAT selection optimization in heterogeneous wireless networks

Recent technological advances in wireless networks will enable the realization of an integrated heterogeneous wireless environment consisting of multiple Radio Access Technologies (RATs) within a network provider. One of the most important benefits is that this will allow providers to balance their traffic among their subsystems without compromising on QoS issues. In this paper we focus on the Network Selection problem to allocate terminals to the most appropriate RATs by jointly examining both users’ and providers’ preferences. We introduce three utility-based optimization functions based on the type of application that users request. We then formulate the terminal assignment problem as an optimization problem, which is recognized as NP-hard. We examine both offline and online selection and develop an optimal Branch and Bound (BB) algorithm, a Greedy heuristic, as well as three Strip Packing variations. BB behaves efficiently in both offline and online environments reducing the search procedure, while the proposed heuristics produce results close to the values we get from BB but with very low computational cost.     

Adaptive scheduling for parallel tasks with QoS satisfaction for hybrid cloud environments

A hybrid cloud integrates private clouds and public clouds into one unified environment. For the economy and the efficiency reasons, the hybrid cloud environment should be able to automatically maximize the utilization rate of the private cloud and minimize the cost of the public cloud when users submit their computing jobs to the environment. In this paper, we propose the Adaptive-Scheduling-with-QoS-Satisfaction algorithm, namely AsQ, for the hybrid cloud environment to raise the resource utilization rate of the private cloud and to diminish task response time as much as possible. We exploit runtime estimation and several fast scheduling strategies for near-optimal resource allocation, which results in high resource utilization rate and low execution time in the private cloud. Moreover, the near-optimal allocation in the private cloud can reduce the amount of tasks that need to be executed on the public cloud to satisfy their deadline. For the tasks that have to be dispatched to the public cloud, we choose the minimal cost strategy to reduce the cost of using public clouds based on the characteristics of tasks such as workload size and data size. Therefore, the AsQ can achieve a total optimization regarding cost and deadline constraints. Many experiments have been conducted to evaluate the performance of the proposed AsQ. The results show that the performance of the proposed AsQ is superior to recent similar algorithms in terms of task waiting time, task execution time and task finish time. The results also show that the proposed algorithm achieves a better QoS satisfaction rate than other similar studies.     

Optimal precomputation for mapping service level agreements in grid computing

A complicated task running on the grid system is usually made up of many services, each of which typically offers a better service quality at a higher cost. Mapping service level agreements (SLAs) optimally is to find the most appropriate quality level for each service such that the overall SLA of a task is achieved at the minimum cost. This paper considers mapping the execution time SLA in the case of the discrete cost function, which is an NP-hard problem. Due to the high computation of mapping SLAs, we propose a precomputation scheme that makes the selection of each individual service level in advance for every possible SLA requirement, which can reduce the request response time greatly. We use a (1+ε)-approximation method, whose solution for any time bound is at most (1+ε) times of the optimal cost. Simulation results demonstrate the superiority of our method compared with others.     

基于非协作博弈的边缘分布式缓存方案

随着多媒体数据流量的急剧增长,传统云计算模式难以满足用户对于低延时和高带宽的需求.虽然边缘计算中基站等边缘设备拥有的计算能力以及基站与用户之间的短距离通信能够使用户获得更高的服务质量,但是如何利用边缘节点的收益和成本之间的关系设计边缘缓存策略,仍然是一个具有挑战性的问题.利用5G和协作边缘计算技术,在大量短视频应用场景下,提出了一种协作边缘缓存技术来同时解决以下3个问题：（1）通过减少传输延时,提高了用户的服务体验;（2）通过近距离传输,降低了骨干网络的数据传输压力;（3）分布式的工作模式减少了云服务器的工作负载.首先定义了一个协作边缘缓存模型,其中,边缘节点配备有容量有限的存储空间,移动用户可以接入这些边缘节点,一个边缘节点可以服务多个用户;其次,设计了一个非协作博弈模型来研究边缘节点之间的协作行为,每一个边缘节点看成一个玩家并且可以做出缓存初始和缓存重放策略;最后,找到了该博弈的纳什均衡,并设计了一个分布式的算法以达到均衡.实验仿真结果表明,提出的边缘缓存策略能够降低用户20%的延时,并且减少了80%的骨干网络的流量.     

Cost-effective capacity migration of Peer-to-Peer social media to clouds

Social media streaming has become one of the most popular applications over the Internet. We have witnessed the successful deployment of commercial systems with CDN (Content Delivery Network)- based engines, but they suffer from excessive costs for deploying dedicated servers. And with the further expansions on network traffic of social media streaming, a cost-effective solution remains an illusive goal. The emergence of cloud computing sets out to meet the challenge by dynamically leasing cloud servers. This paper aims to realize the capacity migration of social media systems to clouds at the reduced cost. Firstly, by lowering the capacity requested from clouds to reduce the capacity migration cost. Based on the crawled data from YouTube which is the most representative online social media, we find that with larger than 90% probability, the YouTube user’s all requested videos are within three hops of related videos. Then the three hops of related videos are regarded as a cluster and a user’s request can be partly satisfied by other users who watch videos in the same cluster to lessen the capacity requested from clouds. Therefore the capacity migration for clusters is under the P2P (Peer-to-Peer) paradigm and a cloud-assisted P2P social media system is proposed. Secondly, given the diverse capacities, cost, limited lease size of cloud servers, we formulate an optimization problem about how to lease cloud servers to minimize the leasing cost and a heuristic solution is presented. The evaluation based on the crawled data from a cluster of YouTube videos shows the efficiency of the proposed schemes.     

基于移动云计算的计算迁移能效算法

移动云计算可以通过应用任务的计算迁移降低执行延时和改善移动设备能效,但面对多云站点选择时,迁移决策是NP问题。针对该问题,提出一种能效计算迁移算法。为了实现截止期限和预算约束下执行时间与代价的多目标优化,算法将优化过程分解为三步进行。首先根据用户对时间与代价参数的偏好,设计一种CTTPO算法对应用进行分割,生成迁移模块（云端站点执行）和非迁移模块（移动设备执行）;然后为了实现云端多站点间的迁移模块调度,设计一种基于教与学最优化方法的MTS算法,进而产生效率最优的应用调度解;最后设计一种基于动态电压缩放方法的ESM算法,通过多站点的性能缩放进一步降低应用执行能耗。通过两种随机应用结构图进行了仿真实验,实验结果证明,该算法在执行效率、执行代价以及执行能耗上要优于对比算法。     

An object replication algorithm for real-time distributed databases

A real-time distributed database system (RTDDBS) must maintain the consistency constraints of objects and must also guarantee the time constraints imposed by each request arriving at the system. Such a time constraint of a request is usually defined as a deadline period, which means that the request must be serviced on or before its time constraint. Servicing these requests may incur I/O costs, control-message transferring costs or data-message transferring costs. As a result, in our work, we first present a mathematical model that considers all these costs. Using this cost model, our objective is to service all the requests on or before their respective deadline periods and minimize the total servicing cost. To this end, from theoretical standpoint, we design a dynamic object replication algorithm, referred to as Real-time distributed dynamic Window Mechanism (RDDWM), that adapts to the random patterns of read-write requests. Using competitive analysis, from practical perspective, we study the performance of RDDWM algorithm under two different extreme conditions, i.e., when the deadline period of each request is sufficiently long and when the deadline period of each request is very short. Several illustrative examples are provided for the ease of understanding. Recommended by: Ashfaq Khokhar     

采用随机规划模型的云资源分配算法

针对云资源提供问题,为了降低云消费者的资源使用成本,提出了一种采用随机规划模型的云资源分配算法.同时考虑按需实例和预留实例,采用两阶段随机整数规划对云资源提供问题进行建模,在资源预留阶段,根据长期的工作负载情况,确定预留实例的类型和数量,在按需分配阶段,根据当前的工作负载,确定动态分配的按需实例的类型和数量.采用抽样平均近似方法减少资源提供问题的场景数量,降低求解复杂度,并提出了一种基于阶段分解的混合进化算法求解资源提供问题.仿真实验结果表明,采用随机规划模型的云资源分配算法能够在较短时间内获得近似最优的云资源预留方案,有效降低了云消费者的资源使用成本.     

基于时间感知排序的云服务QoS预测方法研究

随着云计算理论和技术的成熟,越来越多的云服务得到了蓬勃发展,如何建立高质量的云服务成为了云计算研究领域的一个关键难题。服务质量QoS排序为用户从一系列功能相似的云服务候选者中挑选最优云服务提供了非常有价值的信息。为了获得云服务的QoS值,就需要调用真实的候选云服务。为了避免时间消耗和昂贵的资源浪费,提出了一种基于时间感知排序的云服务QoS预测方法。不同于传统的QoS值预测,基于QoS排序相似度的预测考虑为特定用户检测服务的排序。分时段按权计算出排序相似度,结合时间偏好合成相似度的前k位用户,用来提供信息支持QoS的缺失预测。在WS Dream真实数据集进行的实验研究表明,基于时间感知排序的云服务QoS预测方法有更好的预测精度。     

A policy-oriented secured service for the e-commerce applications in cloud

The communication process is very easy today due to the rapid growth of information technology. In addition, the development of cloud computing technology makes it easier than earlier days by facilitating the large volume of data exchange anytime and from anywhere in the world. E-businesses are successfully running today due to the development of cloud computing technology. Specifically in cloud computing, cloud services are providing enormous support to share the resources and data in an efficient way with less cost expenses for businessmen. However, security is an essential issue for cloud users and services. For this purpose, many security policies have been introduced by various researchers for enhancing the security in e-commerce applications. However, the available security policies are also failing to provide the secured services in the society and e-commerce applications. To overcome this disadvantage, we propose a new policy-oriented secured service model for providing the security of the services in the cloud. The proposed model is the combination of a trust aware policy scheduling algorithm and an effective and intelligent re-encryption scheme. Here, the dynamic trust aware policy-oriented service for allocating the cloud user’s request by the cloud service provider and an effective and re-encryption scheme is used that uses intelligent agent for storing the data in the cloud database securely. The proposed model assures the scalability, reliability, and security for the stored e-commerce data and service access.     

Energy-efficient Tasks Scheduling Heuristics with Multi-constraints in Virtualized Clouds

Reducing energy consumption has become an important task in cloud datacenters. Many existing scheduling approaches in cloud datacenters try to consolidate virtual machines (VMs) to the minimum number of physical hosts and hence minimize the energy consumption. VM live migration technique is used to dynamically consolidate VMs to as few PMs as possible; however, it introduces high migration overhead. Furthermore, the cost factor is usually not taken into account by existing approaches, which will lead to high payment cost for cloud users. In this paper, we aim to achieve energy reduction for cloud providers and payment saving for cloud users, and at the same time, without introducing VM migration overhead and without compromising deadline guarantees for user tasks. Motivated by the fact that some of the tasks have relatively loose deadlines, we can further reduce energy consumption by proactively postponing the tasks without waking up new physical machines (PMs). A heuristic task scheduling algorithm called Energy and Deadline Aware with Non-Migration Scheduling (EDA-NMS) algorithm is proposed, which exploits the looseness of task deadlines and tries to postpone the execution of the tasks that have loose deadlines in order to avoid waking up new PMs. When determining the VM instant types, EDA-NMS selects the instant types that are just sufficient to guarantee task deadline to reduce user payment cost. The results of extensive experiments show that our algorithm performs better than other existing algorithms on achieving energy efficiency without introducing VM migration overhead and without compromising deadline guarantees.