检索结果-内蒙古大学图书馆

PaGrid: A mesh partitioner for computational grids

Journal of Grid Computing 2006年第1期4卷 71-88页

作者： Huang, Sili Aubanel, Eric Bhavsar, Virendrakumar C. Faculty of Computer Science University of New Brunswick Fredericton NB E3B 5A3 Canada

computational grids are emerging as a new infrastructure for high performance computing. Since the resources in a Grid can be heterogeneous and distributed, mesh-based applications require a mesh partitioner that considers both processor and network heterogeneity. We have developed a heterogeneous mesh partitioner, called PaGrid. PaGrid uses a multilevel graph partitioning approach, augmented by execution time load balancing in the final uncoarsening phase. We show that minimization of total communication cost (e.g., as used by JOSTLE) can lead to significant load being placed on processors connected by slow links, which results in higher application execution times. Therefore, PaGrid balances the estimated execution time of the application across processors. PaGrid performance is compared with two existing mesh partitioners, METIS 4.0 and JOSTLE 3.0, for mapping several application meshes to two models of heterogeneous computational grids. PaGrid is found to produce significantly better partitions than JOSTLE and slightly better partitions than METIS in most cases, in terms of estimated application execution time averaged over a large number of runs with different random number seeds. © Springer Science+Business Media, Inc. 2006.

关键词： computational grids Grid middleware Heterogeneous computing Mesh partitioning Multilevel graph partitioning

来源：评论

学校读者我要写书评

暂无评论

Fault Tolerance and Recovery of Scientific Workflows on computational grids 08

Fault Tolerance and Recovery of Scientific Workflows on Comp...

引用

8th IEEE International Symposium on Cluster Computing and the Grid

作者： Kandaswamy, Gopi Mandal, Anirban Reed, Daniel A. Univ N Carolina Renaissance Comp Inst Chapel Hill NC 27517 USA

ISBN: (纸本)9781424442379

In this paper, we describe the design and implementation of two mechanisms for fault-tolerance and recovery for complex scientific workflows on computational grids. We present our algorithms for over-provisioning and migration, which are our primary strategies for fault-tolerance. We consider application performance models, resource reliability models, network latency and bandwidth and queue wait times for batch-queues on compute resources for determining the correct fault-tolerance strategy. Our goal is to balance reliability and performance in the presence of soft real-time constraints like deadlines and expected success probabilities, and to do it in a way that is transparent to scientists. We have evaluated our strategies by developing a Fault-Tolerance and Recovery (FTR) service and deploying it as a part of the Linked Environments for Atmospheric Discovery (LEAD) production infrastructure. Results from real usage scenarios in LEAD show that the failure rate of individual steps in workflows decreases from about 30% to 5% by using our fault-tolerance strategies.

关键词： computational grids fault tolerance and recovery resilient scientific workflows scheduling

来源：评论

学校读者我要写书评

暂无评论

Running Bag-of-Tasks applications on computational grids:: The MyGrid approach

Running Bag-of-Tasks applications on computational grids:: T...

引用

International Conference on Parallel Processing

作者： Cirne, W Paranhos, D Costa, L Santos-Neto, E Brasileiro, F Sauvé, J Silva, FAB Barros, CO Silveira, C Univ. Fed. de Campina Grande Brazil

ISBN: (纸本)0769520170

We here discuss how to run Bag-of-Tasks applications on computational grids. Bag-of-Tasks applications (those parallel applications whose tasks are independent) are both relevant and amendable for execution on grids. However, few users currently execute their Bag-of-Tasks applications on grids. We investigate the reason for this state of affairs and introduce MyGrid, a system designed to overcome the identified difficulties. MyGrid provides a simple, complete and secure way for a user to run Bag-of-Tasks applications on all resources she has access to. Besides putting together a complete solution useful for real users, MyGrid embeds two important research contributions to grid computing. First, we introduce some simple working environment abstractions that hide machine configuration heterogeneity from the user. Second, we introduce Work Queue with Replication (WQR), a scheduling heuristics that attains good performance without relying on information about the grid or the application, although consuming a few more cycles. Note that not depending on information makes WQR much easier to deploy in practice.

关键词： grid computing processor scheduling parallel processing Bag-of-Tasks applications computational grid MyGrid approach scheduling heuristic machine configuration work queue replication WQR Grid computing computational grids Machine Configuration scheduling of multiprocessor PARALLEL PROCESSING (COMPUTERS)

来源：评论

学校读者我要写书评

暂无评论

Study on computational grids in Placement of Wind Turbines Using Genetic Algorithm

Study on Computational Grids in Placement of Wind Turbines U...

引用

World Non-Grid-Connected Wind Power and Energy Conference

作者： Wang, Feng Liu, Deyou Zeng, Lihua Hohai Univ Coll Water Conservancy & Hydropower Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781424447022

To optimize the placement of wind turbines using a genetic algorithm for the fixed size of wind farm, the appropriate computational grids are the basis of the succeeding work. The optimized scheme was tightly restricted by the rationality and accuracy of computational grids. In this paper, based on the consideration of actual wind and wake characteristics of wind turbines, the (a) shape of the grids, (b) arranging the direction of the grids, and (c) the density of the grids were introduced to study the effect of computation grids on the optimization results. Furthermore, the grids' division method in the scheme's optimization of wind turbines placement under different conditions was discussed to increase the power capacity of the wind farm to obtain the maximum benefit of the investment.

关键词： wind turbines micro-siting optimization genetic algorithm computational grids

来源：评论

学校读者我要写书评

暂无评论

Satellite image processing on computational grids

Satellite image processing on computational grids

引用

9th WSEAS International Conference on Automatic Control, Modeling and Simulation

作者： Petcu, Dana Panica, Silviu Eckstein, Andrei Western Univ Timisoara Dept Comp Sci Timisoara 300223 Romania

ISBN: (纸本)9789608457720

Remote sensing image processing is a very demanding procedure in terms of data manipulation and computing power. Grid computing is a possible solution when the required computing performance or data sharing is not available at the user's site. Two scenarios of using Service grids were analyzed in our papers [17, 181. This paper discusses another scenario of using computational grids. According to this scenario a prototype code for satellite image classification was designed, implemented and tested.

关键词： computational grids image processing remote sensing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Structured Parallelism for computational grids 07

Adaptive Structured Parallelism for Computational Grids

引用

ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming

作者： Gonzalez-Velez, Horacio Cole, Murray Univ Edinburgh Sch Informat Edinburgh EH9 3JZ Midlothian Scotland

No abstract available.

ISBN: (纸本)9781595936028

No abstract available.

关键词： Structured Parallelism Algorithmic Skeletons Parallel Language Constructs Patterns computational grids

来源：评论

学校读者我要写书评

暂无评论

Integrating Wireless Sensor Networks with computational grids

Integrating Wireless Sensor Networks with Computational Grid...

引用

1st ICST International Workshop on Security in Emerging Wireless Communication and Networking Systems (SEWCN 2009)

作者： Preve, Nikolaos Natl Tech Univ Athens Sch Elect & Comp Engn Zografos 15773 Greece

ISBN: (纸本)9783642115257

Wireless sensor networks (WSNs) have been greatly developed and emerged their significance in a wide range of important applications such as acquisition and process information from the physical world. The evolvement of Grid computing has been based on coordination of distributed and shared resources. A Sensor Grid network can integrate these two leading technologies enabling real-time sensor data collection, the sharing of computational and storage grid resources for sensor data processing and management. Several issues have occurred from this integration which dispute the modern design of sensor grids. In order to address these issues, in this paper we propose a sensor grid architecture supporting it by a testbed which focuses on the design issues and on the improvement of our sensor grid architecture design.

关键词： Wireless Sensor Networks computational grids Sensor Grid

来源：评论

学校读者我要写书评

暂无评论

A Game-Theoretic and Hybrid Genetic Meta-Heuristics Model for Security-Assured Scheduling of Independent Jobs in computational grids

A Game-Theoretic and Hybrid Genetic Meta-Heuristics Model fo...

引用

4th International Conference on Complex, Intelligent and Software Intensive Systems (CICIS)

作者： Kolodziej, Joanna Xhafa, Fatos Univ Bielsko Biala Dept Math & Comp Sci Ul Willowa 2 Bielsko Biala Poland Birkbeck Univ London Dept Comp Sci & Informat Syst London WC1E 7HX England

ISBN: (纸本)9780769539676

Scheduling independent tasks in computational grids commonly arises in many Grid-enabled large scale applications. Much of current research in this domain is focused on the improvement of the efficiency of the Grid schedulers, both at global and local levels, which is the basis for Grid systems to leverage large computing capacities. However, unlike traditional scheduling, in Grid systems security requirements are very important to scheduling tasks/applications to Grid resources. The objective is thus to achieve efficient and secure allocation of tasks to machines. In this paper we propose a new model for secure scheduling at the Grid sites by combining game-theoretic and genetic-based meta-heuristic approaches. The game-theoretic model takes into account the realistic feature that Grid users usually perform independently of each other. The scheduling problem is then formalized as a noncooperative non-zero sum game with Nash equilibria as the solutions. The game cost function is minimized, at global and user levels, by using four genetic-based hybrid metaheuristics. We have evaluated the proposed model through a static benchmark of instances, for which we have measured two basic metrics, namely the makespan and flowtime. The obtained results suggest that it is more resilient for the Grid users ( and local schedulers) to tolerate some job delays defined as additional scheduling cost due to security requirements instead of taking a risk of allocating at unreliable resources.

关键词： computational grids Scheduling Noncooperative Games Nash Equilibrium Genetic Algorithms Min-Min heuristic

来源：评论

学校读者我要写书评

暂无评论

Armada: a parallel I/O framework for computational grids

Armada: a parallel I/O framework for computational grids

引用

1st IEEE/AMC International Symposium on Cluster Computing and the Grid

作者： Oldfield, R Kotz, D Dartmouth Coll Dept Comp Sci Sudikoff Lab 6211 Hanover NH 03755 USA

High-performance computing increasingly occurs on "computational grids" composed of heterogeneous and geographically distributed systems of computers, networks, and storage devices that collectively act as a single "virtual" computer. One of the great challenges for this environment is to provide efficient access to data that is distributed across remote data servers in a grid. In this paper, we describe our solution, a framework we call armada. The framework allows applications and dataset providers to flexibly compose graphs of processing modules that describe the distribution, application interfaces, and processing required of the dataset before computation. The armada runtime system then restructures the graph, and places the processing modules at appropriate hosts to reduce network traffic. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： framework parallel I/O computational grids data grids

来源：评论

学校读者我要写书评

暂无评论

An autonomous pricing strategy toward market economy in computational grids

An autonomous pricing strategy toward market economy in comp...

引用

International Conference on Information Technology - Coding and Computing

作者： Yang, J Yang, SB Li, MS Fu, QF Univ Sci & Technol China Dept Comp Sci Hefei 230026 Peoples R China

ISBN: (纸本)0769523153

One of the key steps in economy based grid resource allocation is to make reasonable prices for the grid resources. For resources' prices decide the resource flow in the Grid, further influence Grid resources' trading efficiency. This article, instead of discussing the pricing algorithm, argues an autonomous pricing mechanism that leaves the prices to be decided by the Grid traders within their trading process. We firstly point out the factors that influence the resources' prices;then make out the trading flow for resource consumer agents and provider agents. By doing these, the two trading agents can decide their price due to the dynamic changes of the Grid environment without any manmade interferences. Since price is the core of market economy, the autonomous pricing strategy provides us with a foundation to use the invisible hand of market to allocate the Grid resource.

关键词： grid computing resource allocation pricing autonomous pricing strategy market economy computational grids grid resource allocation consumer agents provider agents trading agents

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：