The rapid advances of network technologies shed light on many aspects of the practicability of large scale ubiquitous computing. grid technology has been recognized as an efficient solution to coordinate large-scale s...
详细信息
The rapid advances of network technologies shed light on many aspects of the practicability of large scale ubiquitous computing. grid technology has been recognized as an efficient solution to coordinate large-scale shared resources and execute complex applications in heterogeneous network environments. The problem of resource management and task allocation has always been one of the main challenges. In this paper, we present an efficient task allocation strategy for distributing tasks onto computing nodes in the underlying heterogeneous networks. The contribution of the proposed technique is to minimize average turnaround time by dispatching tasks to processors with smallest communication ratio. System throughput could be also enhanced by dispersing processor idle time. The proposed technique can be applied to heterogeneous cluster systems as well as computational grid environments, in which the communication costs vary in different clusters. Experimental results show that the proposed scheme outperforms other previous algorithms in terms of throughput and turnaround time.
The computational grid provides a promising platform for the deployment of various high-performance computing applications. A grid system consists of heterogeneous resource domains, while the computational tasks of fi...
详细信息
The computational grid provides a promising platform for the deployment of various high-performance computing applications. A grid system consists of heterogeneous resource domains, while the computational tasks of finite element analysis may differ in demand of computing power. The cost-effective utilization of resources in the grid can be obtained through scheduling tasks to optimal resource domains. Firstly, a cost-effective scheduling strategy is presented for finite element applications. Secondly, aiming at the conjugate gradient solver stemming from finite element analysis, a performance evaluation formula is presented for determining optimal resouree domains, which is derived from phase parallel model and takes the heterogeneous characteristic of resource domains into account. Finally, experimental results show that the presented formula delivers a good estimation of the actual execution time, and indicate that the presented formula can be used to determine optimal resource domains in the grid environment.
We present a framework for making computation offloading decisions in computational grid settings in which schedulers determine when to move parts of a computation to more capable resources to improve performance. Suc...
详细信息
We present a framework for making computation offloading decisions in computational grid settings in which schedulers determine when to move parts of a computation to more capable resources to improve performance. Such schedulers must predict when an offloaded computation will outperform one that is local by forecasting the local cost (execution time for computing locally) and remote cost (execution time for computing remotely and transmission time for the input/output of the computation to/from the remote system). Typically, this decision amounts to predicting the bandwidth between the local and remote systems to estimate these costs. Our framework unifies such decision models by formulating the problem as a statistical decision problem that can either be treated "classically" or using a Bayesian approach. Using an implementation of this framework, we evaluate the efficacy of a number of different decision strategies (several of which have been employed by previous systems). Our results indicate that a Bayesian approach employing automatic change-point detection when estimating the prior distribution is the best performing approach.
The paper presents a multi-level scheduling algorithm for global optimization in grid computing. This algorithm provides a global optimization through a cross-layer optimization realized by decomposing the optimizatio...
详细信息
The paper presents a multi-level scheduling algorithm for global optimization in grid computing. This algorithm provides a global optimization through a cross-layer optimization realized by decomposing the optimization problem in different sub-problems each of them corresponding to one among the grid layers such as application layer, collective layer and fabric layer. The QoS of an abstraction level is a utility function that assigns at every level a different value and that depends on the kind of task that is executed on the grid. The global QoS is given by processing of the utility function values of the three different levels, using the Lagrangian method. Multi-level QoS scheduling algorithm is evaluated in terms of system efficiency and their economic efficiency, respectively. Economic efficiency includes user utility, service provider's revenue and grid global utility. System efficiency includes execution success ratio and resource allocation ratio. (C) 2007 Elsevier Ltd. All rights reserved.
The Upper Baker River Dam utilizes a combination of a floating surface collector (FSC) and a guide net to facilitate the downstream migration of anadromous juvenile fish. The FSC generates attraction currents by withd...
详细信息
The Upper Baker River Dam utilizes a combination of a floating surface collector (FSC) and a guide net to facilitate the downstream migration of anadromous juvenile fish. The FSC generates attraction currents by withdrawing water from the forebay, upstream of the guide net. The withdrawn water is discharged at the rear of the FSC by two pumps. A three-dimensional (3D) computational fluid dynamics (CFD) model of the forebay of the dam is presented in this paper. The objective was to investigate forebay hydrodynamics generated by the FSC and operation of the powerhouse. The CFD model, consisting of approximately one million computational cells, was validated against field data. Model results were analyzed, using a recently proposed strain-velocity-pressure (SVP) hypothesis, to identify hydrodynamic cues responsible for attracting juvenile fish to the FSC. The CFD model indicates that the FSC pumps generated high velocity jets dominate the circulation pattern downstream of the guide net. Upstream of the guide net, the velocities are weak, except in the region impacted by attraction currents. The sweeping and normal velocities on the guide net are smaller than those suggested by regulatory agencies for designing screens at juvenile fish collection facilities. Copyright (C) 2008 John Wiley & Sons, Ltd.
computational grids are useful tools for bringing supercomputing power to users by using idle resources in the network. In the following paper we give a short overview of architecture of the Alchemi grid developed on ...
详细信息
ISBN:
(纸本)9781424423835
computational grids are useful tools for bringing supercomputing power to users by using idle resources in the network. In the following paper we give a short overview of architecture of the Alchemi grid developed on Net platform. We created a grid application, which utilizes Rabin-Karp string searching algorithm to test Alchemi grid performances in situation when requests put diverse demands for computing resources to the different grid nodes. Scheduling and dispatching jobs to the computing resources is a critical activity of the grid software. We present a scheduling algorithm which showed performance improvements to the original algorithm shipped with Alchemi grid software.
Extracting useful information from a very large amount of biomedical texts is an important and difficult activity in biomedicine field. Data to be examined are generally unstructured and the available computational re...
详细信息
ISBN:
(纸本)9783540859833
Extracting useful information from a very large amount of biomedical texts is an important and difficult activity in biomedicine field. Data to be examined are generally unstructured and the available computational resources do not still provide adequate mechanisms for retrieving and analyse very large amount of contents. In this paper we present a rule-based system for Text Mining process applied in biomedical textual documents. This application requires a strongly use of the computational resource to perform intensive operations. We propose a grid computing approach to improve application performance.
This paper presents an agent-based computational grid (ACG), which applies the concept of computational grid to agents. The ACG system is to implement a uniform higher-level management of the computing resources and s...
详细信息
This paper presents an agent-based computational grid (ACG), which applies the concept of computational grid to agents. The ACG system is to implement a uniform higher-level management of the computing resources and services on the grid, and provide users with a consistent and transparent interface for accessing such services. All entities in the grid environment including computing resources and services can be represented as agents. Each entity is registered with a grid service manager. Service requestor agent locates a specific grid service by submitting requests to the grid service manager with descriptions of required services. XML is used to describe both grid service descriptions and service requestor agent's queries. An ACG grid service can be a service agent that provides the actual grid service to the other grid member. In this paper, firstly, the conceptual model about ACG grid is described, and then the design and implementation are given. Finally, some conclusions are given. (C) 2003 Elsevier Inc. All rights reserved.
This paper presents a competitive proportional resource allocation in computational grid. A system model is described that allows agents representing various grid resources, which owned by different real world enterpr...
详细信息
This paper presents a competitive proportional resource allocation in computational grid. A system model is described that allows agents representing various grid resources, which owned by different real world enterprises, to coordinate their resource allocation decisions without assuming a prion cooperation. The grid task agents buy resources to complete tasks. grid resource agents charge the task agents for the amount of resource capacity allocated. Two types of optimization problems related to grid task agent are proposed. Given grid resource agent's pricing policy, the task agent optimization problem is to complete its job as quickly as possible when spending the least possible amount of money. Given specified amount of time to complete jobs, the task agent optimization problem is to minimize the cost accrued. This paper provides a price-directed proportional resource allocation algorithm for solving the grid task agent resource allocation problem. Experiments are made to compare the performance of the price-directed resource allocation with conventional Round-Robin allocation. The results of experiment show the price-directed allocation has better performance than usual Round-Robin allocation. (C) 2004 Elsevier B.V. All rights reserved.
Fast computer networks and overperformanced computers enable computational grid establishment on non-dedicated and geographically distributed computers. This causes an increase in dynamic heterogeneity which makes res...
详细信息
ISBN:
(纸本)0780385667
Fast computer networks and overperformanced computers enable computational grid establishment on non-dedicated and geographically distributed computers. This causes an increase in dynamic heterogeneity which makes resource management much more difficult. An additional problem is represented by a strong dependency of resource availability on a human as their owner. Concession of resources to the grid is basically computer supported cooperative work. The described meeting scheduling model points out properties of a human, application requests, organizational and timing properties of meetings, as well as scheduling. Resource selection is also done based on properties of the owner. Evaluation of the proposed approach is carried out on the basis of results obtained in a simplified testing environment Extending the mapping procedure by the meeting scheduling model makes success of the application execution in non-dedicated environment comparable to the execution on reserved resources.
暂无评论