Showing papers in "Future Generation Computer Systems in 2005"

TL;DR: A taxonomy of grid monitoring systems is proposed, which is employed to classify a wide range of projects and frameworks and captures a given system's scope, scalability, generality and flexibility.

TL;DR: It is shown that the Xtrem Web system can tolerate massive failure and the performance of the node protection mechanism is discussed, and the convergence between Global Computing systems and Grid is discussed.

TL;DR: The solution to this problem developed in the framework of the European DataGrid and the Virtual Organization Membership Service (VOMS), which allows a fine grained control of the use of the resources both to the users' organizations and to the resource owners.

TL;DR: This work demonstrates that AI techniques can be utilised to achieve effective workload and resource management in dynamic grid resources management through a combination of intelligent agents and multi-agent approaches.

TL;DR: Two algorithms that use the predictive models to schedule jobs at both system level and application level, and show that the scheduling system using the adaptive scheduling algorithms can allocate service jobs efficiently and effectively are developed.

TL;DR: The requirements, architecture and implementation of GridICE, a monitoring service for Grid systems, are presented and the suitability of this tool in real-life scenarios is analyzed and discussed.

TL;DR: Computational aspects of automatic differentiation applied to global ocean circulation modeling and state estimation and hand-written adjoint routines are provided to retain scalability of domain decomposition-based parallelism.

TL;DR: This paper examines how the super-peer model can handle membership management and resource discovery services in a multi-organizational Grid and a simulation analysis evaluates the performance of a resource discovery protocol.

TL;DR: FastOpt's new automatic differentiation tool TAF is applied to the two-dimensional Navier-Stokes solver NSC2KE, suggesting that the performance of the N SC2KE adjoint may well be generalised to more complex three-dimensional CFD codes.

TL;DR: A heuristic Qsufferage is presented to schedule the bag-of-tasks application in the grid environment, and the result of the experiment shows that Q sufferage algorithm can obtain better performance compared to the other four existing algorithms.

TL;DR: A rationale for extending Web services to distributed simulation environments is presented, together with a description and examples of the integration methodology used to develop significant prototype implementations, and it is argued for combining the power of Grid computing with Web Services to further expand this demanding computation and database access environment.

TL;DR: Several learning methods for RBF networks and their combinations are presented, a gradient-based learning, the three-step algorithm with unsupervised part, and an evolutionary algorithms are introduced, and their performance compared on benchmark problems from the Proben 1 database.

TL;DR: A static data-flow analysis called "to be recorded" analysis is introduced for the determination of certain values that are computed and overwritten in the original program and made available in the adjoint program to guarantee correctness.

TL;DR: The design and implementation of a replica management Grid middleware that was developed within the EDG project is presented and is designed to be extensible so that user communities can adjust its detailed behavior according to their QoS requirements.

TL;DR: The system presented in this paper supports the user in composing an application workflow from existing Grid services with a flow composition system that builds workflows on an abstract level with semantic and syntactic descriptions of services available on the Grid.

TL;DR: To show the feasibility of the developed concepts and elaborate the basis for a dynamic version they have been seamlessly integrated into OGSA-DAI to provide a non-proprietary, centralized and easy to integrate solution.

TL;DR: An enhanced prediction scheme is described, which uses recent fire history and optimization techniques to predict near future propagation and takes advantage of the computational power offered by distributed systems to accelerate the optimization process at real time.

TL;DR: Examples for the usage of Nimrod in molecular modeling are presented, including the parameterization of a group difference pseudopotential (GDP) and a high-throughput workflow infrastructure for computational chemistry.

TL;DR: In this article, the authors present the use of numerical simulations coupled with optimization techniques in oil reservoir modeling and production optimization and describe three main components of an autonomic oil production management framework, which implements a dynamic, data-driven approach and enables Grid-based large scale optimization formulations in reservoir modeling.

TL;DR: This paper describes an interesting grid workflow in atmospheric sciences and shows how it can be implemented using Web Services and an interesting attribute of the implementation technique is that the application codes can be adapted to work on the Grid without source modification.

TL;DR: This paper describes a utility-based framework to determine the components of the contract and formulate the associated resource allocation problem, and considers the resource allocationProblem for a flash crowd scenario and how the contract mechanism implemented using a centralized server can be used to quickly create pseudoservers that can serve out the requests.

TL;DR: A federate migration protocol that bypasses the shortcomings identified above has been developed and better migration performance is achieved and experimental results with comparison to the approach using federation wide synchronization are discussed.

TL;DR: The results suggest that the combined GA/ANN approach may be useful for early detection of AD and that single channel EEG data might be enough to recognize AD.

TL;DR: The topological space properties of the resource space are presented based on the definition of a distance in the space and the construction of a quotient space structure and the proposed theory ensures the RSM to correctly and efficiently specify and manage resources.

TL;DR: This paper reviews the performance of the JXTA networks using benchmarking, based on the proposed performance model, and the two major versions of thc JXta protocol implementations are surveyed and discussed.

TL;DR: A new dynamic load balancing approach named scheduler-worker parallel paradigm is proposed and evaluated, which aims to reduce its runtime significantly and achieve efficiently mapping onto a hierarchical grid system as the computing platform.

TL;DR: This paper proposes a single definition of a Grid network resource abstraction for multiple types of network connectivity and successfully implemented and tested in a network resource management prototype supporting a variety of network technologies.

TL;DR: This paper presents a simple nonlinear procedure for time-series forecasting, based on the use of vector quantization techniques; the values to predict are considered as missing data, and the vector quantification methods are shown to be compatible with such missing data.

TL;DR: An interactive framework called user hints for having humans help optimization methods to solve difficult problems is presented and an evaluation of some user hints systems indicates that optimization processes can benefit from human interaction.

TL;DR: P2P infrastructure, computational resource management in a global-computing setting, the design of scientific applications over P2P infrastructures, and mechanisms that deal with the intrinsic lack of trust in P1P environments are addressed.