目前信息分类提取方法不能满足用户在大数据时代下的信息获取速度需求,为此,提出了基于大数据中心存储信息分层分类优化的信息提取方法.提取数据信息的特征,对得到的信息特征进行校对和调整,在获得存储机制下大量信息的关键特征后,采用信息校验方法消除冗余信息,在信息的校验过程中获取冗余信息的二维坐标,根据这个坐标进行二次检验,确保冗余信息完全消除.利用获取的信息关键特征系数,对比校验区域信息,完成对信息的精确检测,保证信息分类分层优化的有效性.将优化后的信息作为分层分类信息提取的样本,通过条件假设和似然比对事件的发生概率的计算结果确定事件的发生概率,实现对分层分类优化后信息的提取.仿真结果证明,所提方法在提取大数据中心存储信息时,具有速度快、准确率高、信息损失量低等特点.

The emergence of cloud computing can help enterprises reduce their hardware and software investment and save their own operation and maintenance costs, thus more and more enterprises deploy their applications into the cloud. Generally, components of enterprise applications are resided in virtual machines and then hosted by physical machines. In order to achieve the efficiency and utilization of physical machines, reasonable virtual machines placement becomes very important. In this paper we propose a scheme of resource allocation model for virtual machines placement and investigate it with convex optimization approach. We also present a heuristic algorithm to achieve the optimal resource allocation and discuss its equilibrium and stability by applying the asymptotic stability of the continuous dynamic system of Lyapunov stability theory. Finally, we give some numerical examples to illustrate the performance of the resource allocation scheme and confirm its convergence with a certain number of iterations.

Concept drift involving noise is an important research in the field of data mining. Many concept drift detection models are proposed to promote the research of traditional concept drift detection. In this paper, we propose an anti-noise concept drift processing algorithm based on entropy of information, named ACPJS. In ACPJS, the JS-divergence and Hoeffding Bounds are used to set double threshold for concept drift detection and subsequently a horizontal integrated model will be constructed for anti-noise concept drift processing. In the comparison experiments of multiple data sets, the presented algorithm has shown good performance in concept drift detection, anti-noise performance and classification accuracy.

为优化云计算系统的性能、提高资源利用率的同时考虑用户的QoS需求,提出一种将云计算系统研究和工作流集成的优化调度算法.采用有向非循环图DAG建立任务调度模型,将调度划分为两个阶段:基于QoS需求中时间、费用约束,提出一种粒子群优化算法IPSO,应用Pareto进行多目标优化设计;根据系统的负载情况进行调度,提出一种基于负载感知的调度策略.实验结果表明,分阶段的优化调度算法在优化任务调度、提高系统效率的同时提升了资源利用率.

为解决同类型任务在云制造系统中并行执行时资源需求不均衡以及资源的利用率不高的问题.建立了以成本最低化、时间最小化、可靠度最高化、质量最优化为目标的任务资源调度模型.采用基于参考点的非支配排序遗传算法(NSGA-Ⅲ),结合实数矩阵编码方式以及基于实数编码的交叉变异策略代替普通的进化策略对模型进行求解,使用基于层次分析法和熵值法的组合优化决策方法对结果进行评价.分别讨论了资源充足和资源受限时调度系统的性能,通过实例证明该方法是可行的.

This paper considers reasonable bandwidth allocation for multiclass services in peer-to-peer (P2P) networks, measures the satisfaction of each peer as a customer by a utility function when acquiring one service, and develops an optimization model for bandwidth allocation with the objective of utility maximization. Elastic services with concave utilities are first considered and the exact expression of optimal bandwidth allocation for each peer is deduced. In order to obtain an optimum in distributed P2P networks, we develop a gradient-based bandwidth allocation scheme and illustrate the performance with numerical examples. Then we investigate bandwidth allocation for inelastic services with sigmoidal utilities, which is a nonconvex optimization problem. In order to solve it, we analyze provider capacity provisioning for bandwidth allocation of inelastic services and modify the update rule for prices that service customers should pay. Numerical examples are finally given to illustrate that the improved scheme can also efficiently converge to the global optimum.

云任务-资源匹配环节脱节是云端融合过程的突出问题,针对该问题,考虑任务和资源的双边满意度,提出一种基于改进知识迁移极大熵聚类算法(Knowledge transfer maximum entropy clustering algorithm,KT-MECA)的云端融合任务分配模式.该算法改进了历史聚类中心知识和历史隶属度知识的引入方式,提高了聚类性能和稳定性,解决了传统聚类算法不能适用于动态云资源聚类的问题.并考虑双边主体满意度,将该算法的聚类结果应用于云任务-资源的双边匹配决策优化模型中,通过实例证明该方法是可行的.

Data replica management is an important part of cloud computing system.When processing massive data in a cloud computing system,the existing algorithms for data storage and resource scheduling do not consider the dynamics and reliability of data replicas.We therefore propose a dynamic replica placement mechanism based on the domain structure.It takes into full account the number and position of data replicas,as well as the cost of system resources such as memory and bandwidth when a replica is produced.Firstly,according to the information of the replica,the data with high access frequency and long average response time,are replicated,and how to calculate the number of replicas is explained.Secondly,in order to reduce the selection range of nodes of the replica distribution,we propose a dynamic replica placement algorithm,which can choose the range of placement for the replicas according to domain division.Experimental results show that the proposed algorithm can significantly reduce the waste of storage space for the replica with low access frequency,as well as the transmission delay across nodes for the replicas with high access frequency.Besides,it effectively improves the access efficiency to data files in cloud storage systems,the load balance,and the reliability and availability of cloud storage systems.

Aiming at establishing a shared storage environment, cloud storage systems are typical applications of cloud computing. Therefore, data replication technology has become a key research issue in storage systems. Considering the performance of data access and balancing the relationship between replica consistency maintenance costs and the performance of multiple replicas access, the methods of replica catalog design and the information acquisition method are proposed. Moreover, the deputy catalog acquisition method to design and copy the information is given. Then, the nodes with the global replica of the information replicate data resources, which have the high access frequency and the long response time. Afterwards, the Markov chain model is constructed. And a matrix geometric solution is used to export the steady-state solution of the model. The performance parameters in terms of the average response time, finish time, and the replica frequency are given to optimize the number of replicas in the storage system. Finally, numerical results with analysis are proposed to demonstrate the influence of the above parameters on the system performance.

为了更好地提高云计算资源的利用率,设计了基于服务等级协议(Service-Level Agreement,SLA)的云计算资源智能调度实验,从分配成本、迁移成本和违约成本三方面构造了云计算资源智能调度的成本函数,并将蝙蝠算法应用到云计算资源智能调度过程中,进行资源智能调度寻优,达到资源调度代价最小的目的.最后通过CloudSim云平台进行模拟仿真,结果表明该实验方法明显优于传统的粒子群调度算法,在执行成本、资源利用率方面都有很大改进,提高了云计算系统的资源调度能力,是一种有效的调度方法.

In order to improve the resource utilization of cloud computing systems and optimize the system perfor-mance, by taking into account the users` QoS demand, a workflow cloud computing system is established by integrating cloud computing with workflow, and a two-stage resource scheduling model is constructed for the cloud computing workflow system.In the first stage, by considering the time and cost constraints of QoS, the dependencies among the tasks in the workflow, and the processing of the intermediate data from each task, a modified particle swarm optimization algorithm (MPSO) is proposed, and the Pareto is used to obtain an optimal solution so as to improve scheduling efficiency.In the second stage, by considering the resource allocation on hosts, a scheduling stra-tegy with load-aware is proposed to perform resource scheduling according to system loads, so as to improve the resource utilization of the system.Experimental results show that, in the resource scheduling process of the workflow cloud computing system, the modified MPSO algorithm is superior to the earliest heterogeneous finish-time algorithm and single-objective optimization genetic algorithm in terms of execution speed, resource utilization and users` satisfaction with QoS, and that, the proposed scheduling strategy with load-aware can schedule more efficiently accor-ding to the system loads, and the task execution efficiency and the resource utilizationare are thus improved.

Cloud resource management is a topic focus on enhancing the QoS in cloud computing system. This paper discusses a model, that is the adaptive and completion time aware model (ACTA). It gives the job adaptive and completion time aware for resource allocation. Moreover, a strategy is proposed based on the model. Non-cooperative Nash equilibrium theory is used to build the strategy with the goal of aiming to optimize cloud resources allocation. Accordingly, an allocation algorithm based on the gradient projection is presented. With experimental studies, the algorithm for resource scheduling is demonstrated to improve the efficiency of jobs and the cloud computing system resource utilization when compared to the fair scheduling, random scheduling, earliest deadline-time first scheduling.

We propose an economics-oriented cloud computing resources allocation strategy with the use of game theory. Then we develop a resource allocation algorithm named NCGRAA noncooperative game resource allocation algorithm to search the Nash equilibrium solution that makes the utility of various resource providers achieve optimum. We also propose an algorithm named BGRAA bargaining game resource allocation algorithm to further increase the overall revenue with the constraints of efficiency and fairness. Based on numerical results, we discuss the influence of NCGRAA and BGRAA for the utility of resource on the system performance. It shows that the choice of parameters of the two algorithms is significant in improving the system performance and converging to the Nash equilibrium and Nash bargaining.

With the development of mobile Internet and cloud computing,the mobile cloud computing provides a more reasonable solution for the construction of open laboratory.In view of the computer open laboratory problem,this paper discusses the function orientation of the mobile cloud environment laboratory,designs the autonomous experiment model,and further discusses the problems in the management process,to improve computer open laboratory construction level in colleges and universities.

In order to improve the resource utilization and the system performance of cloud computing system, consider the user's QoS demand constraints, integrate the cloud computing and workflow, research scheduling mechanism in the cloud computing workflow system. Firstly, the workflow framework and resource model are proposed based on queue theory. Then considering the QoS requirements of time and cost constraints, an MGA (Improved Genetic Algorithm) algorithm is proposed to optimize system efficiency in resource scheduling stage. Experimental simulation results show that MGA comparing with FCFS (First Come First Service) algorithm and GA (Genetic Algorithm) meets users' QoS needs and the efficiency of the task.

In current datacenters, centers deliver resources for tenants to run various jobs with diverse requirements. Today's resource management can provide higher levels of scheduling options and supports certain QoS (Quality of Service) requirements. However in many references, exiting cloud resource management scheduling focus on the objective function to minimize the deadline time fall short in utility maximization of the resource scheduling in cloud computing. In this paper, we model a resource scheduling problem as a UMM (Utility Maximization Model) to optimize the VM (Virtual Machine) placement policy and a GP (Gradient Projection) algorithm for solving Lagrange problem and optimization is proposed, which also improves the efficiency of resource scheduling comparing of the random algorithm, fair algorithm and earliest-deadline-first algorithm.

Resource of cloud computing has the characteristics of dynamic, distribution, complexity. How to have the effective scheduling according to the users' QoS (Quality of Service) demand and in order to maximize the benefits is the challenge encountered in cloud computing resource allocation. In this paper, according to the characteristics of the resources of cloud computing, considering the constraints of time and budget needs of users, we designed the scheduling model of resource based on particle swarm optimization algorithm, and used the IPSO (Improved Particle Swarm Optimization algorithm) for global search to obtain the multi-objective optimization solutions that satisfies the requirements. Experimental results show that: when the IPSO applied to the resource of cloud computing compares with other algorithms, it has faster response time and could take efficient use of resource to meet the users' QoS requirements in solving multi-objective problems.

According to the dynamic, distribution and complexity of cloud computing, resource scheduling effectively with users' QoS demand and achieving maximum benefit is the unprecedented challenge. To solve the above problem, we propose to use genetic algorithm: design for the crossover operator and build a cloud resource optimization scheduling model that promised to address user needs while optimizing resource allocation. With the experiments, this paper verifies the superiority of models made in this paper. The results show that the use of genetic algorithm to optimize cloud resource scheduling has the rationality and feasibility. Meanwhile, using the genetic algorithm is useful for effectively scheduling of cloud resource meeting the users' QoS.

In order to monitoring and control street lighting, the lighting pole controller was designed and implemented based on wireless sensor network. The controllers were installed at each lighting pole. The hardware of controller integrates a AVR microcontroller, a radio modem, double lamp control units and current detecting units. The lamp control units control primary and secondary lamp on or off according to receiving command from RTU. The current detecting units measure the power line current to determine the lamp status which reporting to the center. A routing strategy based on the sequence controller address was proposed. According to the power substation powering scope, the lighting controller was divided many clusters. The controller forwards the packet to RTU according to the packet head information, sending controller address and its own address. All forwarding controllers waits a random interval and listen other controller transmission to avoid that multiple copies of a same packet is sent. The proposed routing for street lighting system is simple and not need to maintain complex path discovery algorithms.

High-Availability is one of the goals Survivable Storage System pursuing,and there are few evaluation methods for Availability of Survivable Storage System on Secret-Sharing Scheme.A Simple Evaluation Method for Availability(SEMA)and a Markov-chained Evaluation Method for Availability(MEMA)are both proposed,and their description and calculation model are also given.Availability of Survivable Storage System on Secret-Sharing Scheme is evaluated separately by the two evaluation methods,and the results are analyzed in details.In addition,the application scopes of the two evaluation methods are discussed.The two evaluation methods can evaluate Availability of Survivable Storage System on Secret-Sharing Scheme and find the factors affecting the Availability,which is helpful to design a High-Availability Survivable Storage System.