Search

The application of Grid computing has been broadening day by day. An increasing number of users has led to the requirement of a job scheduling process, which can benefit them through optimizing their utility functions. On the other hand, resource providers are exploring strategies suitable for economically efficient resource allocation so that they can maximize their profit through satisfying more users. In such a scenario, economic-based resource management strategies (economic models) have been found to be compelling to satisfy both communities. However, existing research has identified that different economic models are suitable for different scenarios in Grid computing. The Grid application and resource models are typically very dynamic, making it challenging for a particular model for delivering stable performance all the time. In this work, our focus is to develop an adaptive resource management architecture capable of dealing with multiple models based on the models' domains of strengths (DOS). Our preliminary results show promising outcomes if we consider multiple models rather than relying on a single model throughout the life cycle of a Grid. Economic-based approaches are relevant for Grid resource management.Different economic models are found suitable for different scenarios in Grid computing.A quantitative analysis has been carried out to identify the domains of strengths of major economic models in Grid resource management.The opportunities and challenges of developing an optimization framework by utilizing the potentials of different models in different scenarios have been discussed.The development of the optimization framework in the context of dynamic and distributed computing environment has been elaborated.

The access to Grid resources depends on policies defined by the administrators of the physical organizations and of the Grid middleware. This approach does not require support for access control in the middleware, but since changes in the access control policy of the Virtual Organization imply the involvement of one or more administrators, it lacks the flexibility needed in several Grid application scenarios. In this paper we propose a novel Cooperative Access Control model for Grid environments that increases the flexibility of the access control model offered by state-of-the-art Grid platforms without requiring changes in the middleware. The approach is based on collaboration among Grid users and allows them to exchange access permissions to Virtual Resources without the intervention of administrators. We also propose a solution based on Broadcast Encryption which allows to enforce a Cooperative Access Control model on Grids avoiding misuse and granting anonymity. Finally, we show that our solution can be defined on top of the access control mechanisms offered by state-of-the-art Grid middleware and illustrate how the proposed model has been implemented as a service in a service-oriented Grid environment. Highlights? We modeled the current Access Control on Grid and discuss its limitations. ? We enhanced such model with a novel Cooperative Access Control (CAC) model. ? We discussed security issues related to the CAC model. ? We proposed a Broadcast encryption-based solution (BE-CAC) to solve such issues. ? We described the implementation of BE-CAC on an actual Grid.

The Grid-Enabled Computational Electromagnetics (GECEM) portal is a problem-solving environment that uses grid technologies to support scientists in accessing distributed resources for the solution of computational electromagnetics (CEM) problems. These resources include input files specifying the system geometry, and proprietary software and hardware for mesh generation and CEM simulation. Through interacting with a web-based grid portal, a user can access these resources, submit jobs, monitor and execute distributed grid applications, and collaboratively visualize the results of the CEM simulation. Thus, the portal allows users to use Grid infrastructure to share resources among geographically distributed partners in order to execute large-scale computational electromagnetics simulations, and to collaboratively analyze and visualize the results. This paper describes a secure, web-based portal, built on the GridSphere framework, composed of a number of JSR-168 compliant portlets that deploy services at the back end for discovery and management of distributed resources, and for invoking services for mesh generation and CEM simulation. The paper also describes how security is achieved through the Grid Security Infrastructure and single sign-on.

This paper describes the Grid-Service-in-a-Box (GSiB) system-a visual environment for both service providers and service clients who wish to deploy, manage, and use services in a Grid environment, without having to be experts in Grid and Web service technologies. GSiB provides a variety of easy-to-use graphical user interfaces for service providers to deploy, undeploy, update, compose, and monitor services. In addition, service clients can generate service-composite applications, and track and monitor submitted jobs. This paper describes these interfaces and several implementation issues are addressed. An example service-based application is presented to illustrate how a workflow can be used to generate and execute an application on Grid infrastructure.

In spite of the existence of several grid middleware projects, developing and executing programs on the computational grid remains a user intensive process. The goal of the Grid Application Development Software (GrADS) project is to make the grid simpler to use despite the dynamically changing status of grid resources. Protein and genome sequence alignment is a basic operation in bioinformatics, and it requires large data sets and tends to be highly compute intensive. In this paper, we present work done to grid-enable a biological sequence alignment package (FASTA) and to run it under the GrADS framework. We discuss the advantages of using GrADS framework for FASTA.

Many Grid applications require high bandwidth end-to-end connections between Grid resources in different domains. Fiber optic networks, owned by different providers, have to cooperate in a coordinated manner in order to provide an end-to-end connection. Currently, multi-domain optical network solutions require paper-based long-term contracts between administrative domains. This paper describes a solution for dynamically creating optical connections between different autonomous domains. This was implemented in the form of a Grid Service following the Open Grid Service Architecture. In our prototype, each switch belongs to a different network domain. Our Grid Service uses a toolkit based on the Generic Authorization, Authentication, and Accounting framework. This toolkit authorizes the use of optical infrastructure elements based on specific policies that are active within each domain. To complete our multi-domain authorization architecture, a Broker Service was also implemented. Our Broker Service interacts with the Grid Service instances to provide Grid application with a simplified way to set up end-to-end connections on demand.

Computational and data Grids couple geographically distributed resources such as high performance computers, workstations, clusters, and scientific instruments. Grid Workflows consist of a number of components, including: computational models, distributed files, scientific instruments and special hardware platforms. In this paper, we describe an interesting grid workflow in atmospheric sciences and show how it can be implemented using Web Services. An interesting attribute of our implementation technique is that the application codes can be adapted to work on the Grid without source modification.

In this paper we present the new project called GridLab which is funded by the European Commission under the Fifth Framework Programme. The GridLab project, made up of computer scientists, astrophysicists and other scientists from various application areas, will develop and implement the grid application toolkit (GAT) together with a set of services to enable easy and efficient use of Grid resources in a real and production grid environment. GAT will provide core, easy to use functionality through a carefully constructed set of generic higher level grid APIs through which an application will be able to call the grid services laying beneath in order to perform efficiently in the Grid environment using various, dramatically wild application scenarios.