Coordinated global and private job-flow scheduling in grid virtual organizations

In this work, a job-flow scheduling approach for Grid virtual organizations (VOs) is proposed and studied. Users and resource providers preferences, VOs internal policies, resources geographical distribution along with local private utilization impose specific requirements for efficient scheduling according to different, usually contradictive, criteria. With increasing resources utilization level the available resources set and corresponding decision space are reduced. In order to improve overall scheduling efficiency, we propose an anticipation scheduling heuristic. It includes a target (anticipated) pattern solution definition and a special replication procedure for efficient and feasible resources allocation. A proposed anticipation algorithm is compared against conservative backfilling variations using such criteria as average jobs response time (start and finish times) as well as users and VO economic criteria (execution time and cost).

The cooperation of diverse partners carried out in Grid Virtual Organizations (VOs) requires clear specification of each party's capabilities and obligations. The negotiation and enactment of contracts, underpinned by Service Level Agreements (SLAs), is essential for establishing a VO. This paper describes how semantic technologies can simplify this task by employing ontology alignment methods. The application of these techniques is placed in the context of the European Union's Gredia Project and its journalism-related pilot application.

Distributed environments with the users decoupling from resource providers are generally defined as utility Grids. This paper focuses on the problems of an efficient scheduling in virtual organizations (VOs) of utility Grids. The proposed scheduling model ensures the VO stakeholders preferences and provides strategies for effective resources utilization. An approach based on the combination of the cyclic scheduling scheme, backfilling and several heuristic procedures is proposed and studied. Comparative simulation results are introduced for different algorithms and heuristics. Resource domain composition and heterogeneity as well as the VO pricing policy are taken into account. Considered scheduling approaches provide different benefits depending on the VO scheduling objectives. The results justify the use of the proposed approaches in a broad range of the resource environment parameters.

In Grid environments, virtual organizations (VOs) often need to define access control policies to govern who can use which resources for which purpose over multiple policy domains. This is challenging, not only because the entities in VOs must collaborate with each other to share resources across administrative domains, but also because there usually exist a large amount of underlying sites (resource providers) and users in VOs. In this paper, we introduce to use trust management approach to address these problems in Grid environments. We propose a rule-based policy language (RPL) framework to describe the authorization and delegation policies related to VOs, sites and users. This paper also introduces the design of an enhanced community authorization service (ECAS) based on RPL framework, which can be seamlessly integrated with local authorization mechanisms. ECAS uses different kinds of delegation policies for flexible collaboration on authorization between entities in VOs. Compared with similar research works, ECAS enhances the flexibility and scalability of decentralized authorization in Grid environments.KeywordsGridVOAccess ControlTrust Management

While single-domain and application-specific “organized networks” are known and have been in use throughout history, the concept of virtual organizations (VO) as such is very young (Camarinha-Matos, Banahan, & Sousa, 2004). In addition, virtual organizations encompass a wide range of typologies in structure, topology, and time span, as well as life cycle coverage (Karvonen, Salkari, & Ollus, 2005). Even though specific categories of VOs are more and more understood (i.e. supply chains, extended enterprises and other types of networks) and systematically supported by dedicated methods and tools, the “management” of their activities in terms of fostering the coordinated target achievement is still in its beginnings. Hence the management of generic VOs is even less systematically researched, which in itself constitutes a major challenge. It is important to note that VO management is about the management of business processes going over and across the VO members, it is not about the management of the constituent members themselves. VO management denotes the organization, allocation, and coordination of resources and their activities, as well as their interorganizational dependencies, to achieve the objectives of the VO within the required time, cost, and quality frame (ECOLEAD, 2005).

In this paper, we present a role-based access control method for accessing databases through the Open Grid Services Architecture – Data Access and Integration (OGSA-DAI) framework. OGSA-DAI is an efficient Grid-enabled middleware implementation of interfaces and services to access and control data sources and sinks. However, in OGSA-DAI, access control causes substantial administration overhead for resource providers in virtual organizations (VOs) because each of them has to manage a role-map file containing authorization information for individual Grid users. To solve this problem, we used the Community Authorization Service (CAS) provided by the Globus Toolkit to support the role-based access control (RBAC) within OGSA-DAI. CAS uses the Security Assertion Markup Language (SAML). Our method shows that CAS can support a wide range of security policies using role-privileges, role hierarchies, and constraints. The resource providers need to maintain only the mapping information from VO roles to local database roles and the local policies in the role-map files, so that the number of entries in the role-map file is reduced dramatically. Also, unnecessary authentication, mapping and connections can be avoided by denying invalid requests at the VO level. Thus, our access control method provides increased manageability for a large number of users and reduces day-to-day administration tasks of the resource providers, while they maintain the ultimate authority over their resources. Performance analysis shows that our method adds very little overhead to the existing security infrastructure of OGSA-DAI.

A Virtual Organization (VO) in the Grid is a collection of users and distributed resources, in which resources are shared by users. VOs are dynamically created for some goals and then disappear after the goals are achieved. Conventional Grid architectures have been proposed for a single or static VO environment. In this paper, we propose a ticket-based Grid services architecture to support the dynamic VO environment. Tickets contain information and delegated rights of resource providers, VO managers, and users. By using these tickets, the proposed architecture supports various services in the dynamic VO environment, such as VO management, fine-grained authorization, resource information, and resource management.

The execution of large scale grid applications requires the use of several computational resources owned by various Grid Service Providers (GSPs). GSPs must form Virtual Organizations (VOs) to be able to provide the composite resource to these applications. We consider grids as self-organizing systems composed of autonomous, self-interested GSPs that will organize themselves into VOs with every GSP having the objective of maximizing its profit. We formulate the resource composition among GSPs as a coalition formation problem and propose a game-theoretic framework based on cooperation structures to model it. Using this framework, we design a resource management system that supports the VO formation among GSPs in a grid computing system.

An online auction mechanism for cloud computing resource allocation and pricing based on user evaluation and cost

Dynamic inter-domain collaborations and resource sharing comprise two key characteristics of mobile Grid systems. However, inter-domain collaborations have proven to be vulnerable to conflicts that can lead to privilege escalation. These conflicts are detectable in inter-operation policies, and occur due to cross-domain role relationships. In addition, resource sharing requires to be enhanced with resource usage management in virtual organizations where mobile nodes act as resource providers. In this case the enforcement of resource usage policies and quality of service policies are required to be supported due to the limited capabilities of the devices. Yet, the ANSI INCITS 359-2004 standard RBAC model provides neither any policy conflict resolution mechanism among domains, nor any resource usage management functionality. In this paper, we propose the domRBAC model for access control in mobile Grid systems at a low administrative overhead. The domRBAC is defined as an extension of the standardized RBAC by incorporating additional functionality to cope with requirements posed by the aforementioned systems. As a result, domRBAC facilitates collaborations among domains under secure inter-operation, and provides support for resource usage management in the context of multi-domain computing environments, where mobile nodes operate as first-class entities.Keywordsmobile Gridrole based access control (RBAC)secure inter-operationresource usage managementcross-domain authorization

A distributed system such as a grid infrastructure consists of different institutions and organizations that, with the goal of sharing resources with each other, need to establish trust relationships and security policies. Most implemented systems make use of the PKI-compliant grid security infrastructure (GSI) for authentication purposes and use different authorization methods that rely on users' membership in the grid logical domain (the virtual organization). However, each grid site hosting a resource provider needs to set its own admission policies for decentralized management. Focusing on web grid resources, the paper describes security mechanisms acting at global network, VO and target site levels. This papers provides a method based on the Java handlers ' technique available for a resource provider at a target grid site to secure its web resources. Moreover, the paper proposes the future use of an integration system between a VO-based system and federated identity-based infrastructure.

A secure information service for monitoring large scale grids

The article considers the resource allocation and scheduling problem in a grid computing environment. The article proposes system optimisation scheduling (SOS) that provides a potential solution of joint optimisation of objectives for both the resource and application layer, which combine both application-oriented and resource-oriented scheduling benefits. Grid systems will strive to find an optimal relation between user satisfaction and resource utilisation. Utility functions are used to express grid user's Quality of Service requirement, resource provider's benefit function and system's objectives. In order to verify the efficiency of the proposed scheduling algorithm, we compare the performance of application optimisation scheduling, resource optimisation scheduling, SOS with a traditional Round-Robin algorithm. The simulations study the effect of the request rate and task-to-resource ratio on the different scheduling algorithm.

Networks-on-chip (NoC) has been recognized as a scalable approach to cope with the increasingly large demand for on-chip communication. This work focuses on how to achieve guaranteed service for application-specific NoCs through resource reservation. A graph model is adopted to describe physical and temporal sources of an NoC in a unified manner. Based on the graph model, two resource allocation heuristics are proposed and investigated. One heuristic leverages the idea of chip layout routing and the other utilizes Boolean satisfiability. Results from simulation from various testcases indicate that the proposed methods significantly outperform a state-of-the-art previous work.

Grid technologies support collaborative e-Research typified by multiple institutions and resources seamlessly shared to tackle common research problems. The rules for collaboration and resource sharing are commonly achieved through establishment and management of virtual organizations (VOs) where policies on access and usage of resources by collaborators are defined and enforced by sites involved in the collaboration. The expression and enforcement of these rules is made through access control systems where roles/privileges are defined and associated with individuals as digitally signed attribute certificates which collaborating sites then use to authorizeaccess to resources. Key to this approach is that the roles are assigned to the right individuals in the VO; the attribute certificates are only presented to the appropriate resources in the VO; it is transparent to the end user researchers, and finally that it is manageable for resource providers and administrators in the collaboration. In this paper, we present a security model and implementation improving the overall usability and security of resources used in Grid-based e-Research collaborations through exploitation of the Internet2 Shibboleth technology. This is explored in the context of a major new security focused project at the National e-Science Centre (NeSC) at the University of Glasgow in the nanoCMOS electronics domain.