The capability to support resource sharing between different organizations and high-level performance are noteworthy features of gridcomputing. Applications require significant design effort and complex coordination ...
详细信息
The capability to support resource sharing between different organizations and high-level performance are noteworthy features of gridcomputing. Applications require significant design effort and complex coordination of resources to define, deploy and execute components on heterogeneous and often unknown resources. A common trend today aims at diffusing workflow management techniques to reduce the complexity of grid systems through model-driven approaches that significantly simplify application design through the composition of distributed services often belonging to different organizations. With this approach, the adoption of efficient workflow enactors becomes a key aspect to improve efficiency through run-time optimizations, so reducing the burden for the developer, who is only responsible of defining the functional aspects of complex applications since he/she has only to identify the activities that characterize the application and the causal relationships among them. This paper focuses on performance improvements of grid workflows by presenting a new pattern for workflow design that ensures activity pre-scheduling at run-time through a technique that generates fine-grained concurrency with a couple of concepts: asynchronous invocation of services and continuation of execution. The technique is implemented in a workflow enactment service that dynamically optimizes process execution with a very limited effort for application developer. (C) 2008 Elsevier B.V. All rights reserved.
In this paper we present a performance evaluation of a large-scale numerical application on a cluster and a global grid/Cluster platform. The computational resources are a cluster of clusters (34 nodes, 84 processors)...
详细信息
ISBN:
(纸本)9780780394858
In this paper we present a performance evaluation of a large-scale numerical application on a cluster and a global grid/Cluster platform. The computational resources are a cluster of clusters (34 nodes, 84 processors) and a local area network grid (128 nodes), distributed on two geographic sites: Tsukuba university (Japan) and university of Lille I (France). We compare a classical MPI (Message Passing Interface) version with global grid/Cluster versions. We also present and test some techniques for numerical applications on a grid/Cluster infrastructure based on out-of-core programming and an efficient data placement. We discuss the performances of a block-based Gauss-Jordan method for large matrix inversion. As experimental grid middleware we use the XtremWeb system to manage non-dedicated distributed resources.
Dealing with unknown and unpredictable participants in open self-organising systems is a key challenge for current research in the Autonomic and Organic computing communities. Within this paper, we consider distribute...
详细信息
ISBN:
(纸本)9781509016532
Dealing with unknown and unpredictable participants in open self-organising systems is a key challenge for current research in the Autonomic and Organic computing communities. Within this paper, we consider distributed rendering of films based on volunteer-based gridcomputing systems as application scenario. We use this scenario to investigate solution strategies that take computational trust into account to deal with the challenges posed by openness. Therefore, we explain how the concept of trust can be established in such systems and compare the behaviour of two well-known representatives: the Big and Ugly Rendering Project (BURP) running on the Berkeley Open Infrastructure for Network computing (BOINC) and the Trusted Desktop grid (TDG) from the Organic computing domain. We introduce four general cooperation strategies and show that the TDG outperforms BURP in cases with up to 50% attackers considering metrics such as throughput and correctness.
This paper presents a framework of PI grid system, a gridcomputing platform for power systems, which shows how grid technologies and high performance computing can be efficiently used for power system applications. A...
详细信息
ISBN:
(纸本)0780386108
This paper presents a framework of PI grid system, a gridcomputing platform for power systems, which shows how grid technologies and high performance computing can be efficiently used for power system applications. A prototype system is built to enable the distributed unified power How calculation in this gridcomputing environment.
This paper presents and discusses the design and implementation of authorization mechanisms for a data repository service for grid environments that supports secure sharing of possibly confidential data by members of ...
详细信息
ISBN:
(纸本)9781424403431
This paper presents and discusses the design and implementation of authorization mechanisms for a data repository service for grid environments that supports secure sharing of possibly confidential data by members of ad-hoc created groups. Such a system requires the separation of the repository into independent components thus adding to the complexity of the authorization mechanisms that protect both the storage service against unauthorized and possible malicious use, and intellectual property and confidentiality of the user's data. The solution proposed here extends the VOMS architecture, in favor of the other architectures for efficiency. The authorization is group-based with Group Membership Authorization Service responsible for maintaining the user roles in a virtual organization (i.e., the membership in a group). The user can now securely access data in a distributed repository by collecting SAML assertions from the component services and creating a complete assertion document that allows it to retrieve data from a data service.
Coordinated scheduling across multiple sites over the grid has become a possibility due to grid technologies such as Globus and the Silver meta-scheduler This would allow user jobs to be transparently executed at remo...
详细信息
ISBN:
(纸本)0780386949
Coordinated scheduling across multiple sites over the grid has become a possibility due to grid technologies such as Globus and the Silver meta-scheduler This would allow user jobs to be transparently executed at remote sites across the grid, instead of a particular local cluster. Previous research has shown this type of job distribution to be beneficial in terms of average metrics such as loss of capacity and turnaround time. This research has sparked interest in implementing such schemes, for example on the Cluster Ohio system. However: an issue that has not been addressed is that of fairness - will jobs at less loaded sites be significantly adversely affected by the distributed scheduling schemes? Trace based simulations show that indeed, there can be considerable unfairness to the less loaded sites when previously proposed distributed scheduling schemes are used. We assess approaches to enhance fairness to jobs at local sites and show that they improve fairness while also providing very good overall performance.
The HLA-based distributed simulation has neither mechanisms for managing execution according to the dynamically changing conditions of computing resources nor implementation with dynamical discovery. gridcomputing is...
详细信息
ISBN:
(纸本)7506278413
The HLA-based distributed simulation has neither mechanisms for managing execution according to the dynamically changing conditions of computing resources nor implementation with dynamical discovery. gridcomputing is designed to coordinate resources that are not subject to centralized control. Firstly, we present an architecture of distributed Interactive Simulation on grid (DISG) which supports execution of HLA-based Parallel and Advanced distributed Simulation on the gridcomputing Environment. The architecture aims at the technology for constructing distributed interactive simulation on gridcomputing Environment (GCE), partitions the base components of DISG designates the base function and purpose, describes the interrelation and emphasizes the efficient execution mechanism of large-scale distributed simulation system on the GCE. Secondly, we give a prototype to validate the feasibility and examine the performance of the key techniques of DISG. Finally, we present an operational platform, called GlobeSimgrid, by which we demonstrate how ontologies and grid techniques can be integrated together to provide a semantic-heterogeneity solution which, in a certain degree, address the challenge of large-scale distributed simulation system integration.
This paper presents the design of multi-physic integration tool. The goal is to design and implement a high-level support for integration of existing applications. Each application should implement an interface that a...
详细信息
ISBN:
(纸本)9781905088423
This paper presents the design of multi-physic integration tool. The goal is to design and implement a high-level support for integration of existing applications. Each application should implement an interface that allows to steer application and execute data requests. The design supports various coupling strategies, discretization techniques, and also the distributed applications.
Use of renewable and non-renewable sources for distributed energy generation is more efficient than using only one of them standalone. For such distribution system stand-alone grid is considered having no co-ordinatio...
详细信息
ISBN:
(纸本)9781509066216
Use of renewable and non-renewable sources for distributed energy generation is more efficient than using only one of them standalone. For such distribution system stand-alone grid is considered having no co-ordination with conventional grid The proposed system is connecting outputs of different renewable sources to grid via Radio Frequency (RF) communication module. The actual working mechanism of RF communication module is to match phase angle of AC output generated from renewable sources, and in turn combining matching power information of these outputs into stand-alone smart grid Matching phase angles of different outputs from renewable sources, plays extremely crucial role, otherwise grid and other circuitry will get hit by unforeseen damage and casualties may occur. Furthermore, this paper demonstrates the research in area of energy grid with prototype model being build and related findings are shared along with insightful statistically processed real time system data analysis. This paper proposes more in depth insights into subject matter with continuation to our previous paper [1].
暂无评论