- A component-based middleware framework for configurable and reconfigurable Grid computing
Geoff Coulson, Paul Grace and Gordon Blair, et al.
Concurrency and Computation: Practice & Experience, Vol. 18, No. 8, 2006, pp. 865-874.
Significant progress has been made in the design and development of Grid middleware which, in its present form, is founded on Web services technologies. However, we argue that present-day Grid middleware is severely limited in supporting projected next-generation applications which will involve pervasive and heterogeneous networked infrastructures, and advanced services such as collaborative distributed visualization. In this paper we discuss a new Grid middleware framework that features (i) support for advanced network services based on the novel concept of pluggable overlay networks, (ii) an architectural framework for constructing bespoke Grid middleware platforms in terms of "middleware domains" such as extensible interaction types and resource discovery. We believe that such features will become increasingly essential with the emergence of next-generation e-Science applications.
- Dynamic Auto-Adaptive Load-Balance Algorithm for Grid Computing
Keqing Li, Xinmeng Chen and Hui Tan.
Wuhan Daxue Xuebao (Journal of Wuhan University) (Natural Science Edition), Vol. 52, No. 1, 24 Feb. 2006, pp. 69-72.
According to the inherent hierarchy in computer networks, we propose a dynamic auto-adaptive load-balance algorithm, which based on hierarchy. It adopts centric manageable algorithm in the lower hierarchies while distributed high-effect algorithm in the higher one. The load status of system can be described more accurate because of a moderate status added between over loading and low loading, and makes grid computing becomes stable. Overhead and traffic loading maybe decrease due to the loads migrated to neighbor nodes.
- Structured process execution middleware for Grid computing
F. R. L. Cicerre, E. R. M. Madeira and L. E. Buzato.
Concurrency and Computation: Practice & Experience, Vol. 18, No. 6, 2006, pp. 581-594.
Grid computing is a model for wide-area distributed and parallel computing across heterogeneous networks in multiple administrative domains. It strives to provide breakthrough computing power at low cost. Nowadays there are dozens of academic and commercial products that allow execution of isolated tasks on Grids, but few products support the coordination of long-running processes in a distributed fashion. In order to address the subject, this paper presents a programming model and a middleware that support the hierarchical execution of structured processes using available nodes in a Grid environment. Their advantages are adaptable and structured coordination of activities, with better execution scalability, performance, reliability and easy monitoring. This paper also presents results that demonstrate the efficiency of this structured model, supporting dynamic adaptation of process execution through the use of an application that searches for prime numbers.
- A Parallel Approach for Resource Scheduling in Grid Computing Environment
Mohammad Kalantari and Kazem Akbari.
WSEAS Transactions on Computers, Vol. 4, No. 9, Sept. 2005, pp. 1054-1061.
Grid computing has emerged as an important new field, distinguished from conventional distributed computing by its focus on large-scale resource sharing, innovative applications, and high performance orientation. A Grid integrates and coordinates resources and users that live within different control domain with the goal of delivering non-trivial quality of service (QoS). Consequently, scheduling is a fundamental issue in achieving high performance on computational grids. The job scheduling problem for grid computing has been studied as a combinatorial optimization. In this paper, we propose a mathematical neural network based scheduling solution for grid computing environment. Using mathematical method guarantees rapid convergent that is essential for such environments with proliferation of resources.
- Standardizing Grid Computing
Oracle Magazine, Vol. 19, No. 6, Nov.-Dec. 2005, pp. 63-64.
"The EGA has launched an aggressive technical effort to advance standards and architectures for grid computing along five major areas," explains Tony Di Cenzo, Oracle's director of standards strategy and architecture, and alternate representative to EGA's board of directors. "By focusing on grid-style computing in and between enterprise data centers, and on enterprise components-storage, servers, databases, application servers, and management frameworks-the EGA is focusing on the infrastructure and applications that enterprises use to run their businesses. By focusing on these interconnected pools of resources, enterprises can dynamically allocate resources when required to meet critical demand or changing business needs."
- An ant algorithm based grid computing and task scheduling
Z. -H Xu and J. -Z Sun.
Tianjin Daxue Xuebao (J.Tianjin Univ.Sci.Technol.) (China), Vol. 37, No. 5, May 2004, pp. 414-418.
The complex resources and tasks in grid computing environment make it very difficult to validate the methods of resource management and task scheduling. This paper proposes a simulation architecture for grid computing, designs and realizes an ant algorithm based task scheduling method, combines resource management and task scheduling, and gives attention to the quality of service (QoS) and the system load balance. The experimental results are perfect.
- Optimising multicast structures for grid computing
G. Waters, J. Crawford and S. G. Lim.
Computer Communications, Vol. 27, No. 14, Sept. 2004, pp. 1389-1400.
This paper introduces a flexible new method of constructing hierarchical multicast structures suitable for supporting large-scale GRID applications. Hierarchical multicast trees are constructed by repeated application of clustering algorithms that partition the members of a large application community to form a layered hierarchy of clusters of users. The hierarchies are examples of application overlay networks that do not rely on network layer facilities for multicast transmission. The centralized method described applies clustering based either on the geographical location of users or by using more standard network topology measures. Our results show favourable performance when compared with the tree-building algorithm of the NICE protocol for overlay networks. Both NICE and our clustering approach build overlay networks which offer a compromise between the 'stress' on network links and the 'stretch' or increase in delay to users caused by the application layer overlay.
- Divisible load scheduling for grid computing
D. Yu and Th G. Robertazzi.
Fifteenth IASTED International Conference on Parallel and Distributed Computing and Systems; Volume 1; Marina del Ray, CA; USA; 3-5 Nov. 2003; Fifteenth IASTED International Conference on Parallel and Distributed Computing and Systems
The use of divisible load scheduling theory to model and design grid systems such as those arising in large physics experiments is discussed. Current divisible load theory is summarized. A typical application, the STAR experiment at the Relativistic Heavy Ion Collider (RHIC) is discussed. This includes a sample calculation based on existing infrastructure numbers.