Grid Computing Research Research Articles

Grid Computing Research from India: A Bibliometric Assessment of Publications during 2008–2017

The paper examines quality and quantity of scientific research in India as reflected in publications output on grid computing on a series of bibliometric indicators. Data were extracted from Scopus database consisting of 1340 publications in grid computing research from India in 10 years during 2008-17 citation impact of 4.33 citations per paper and international collaborative publication share of 12.16%. The paper profiles global publication output and share of 10 most productive countries in grid computing research, 15 most productive Indian organizations and 15 most productive authors on a series of indicators including publications output, number of citations, the relative citation index, citations per paper, h-index and share of international collaborative papers during 2008-17. Computer science, among top 3 subjects, accounted for the largest publication share (90.15%), followed by engineering (26.79%) and mathematics (13.66%). The 15 most leading organizations and authors together contributed 31.57% and 14.25% as their share of Indian publication output and 44.93% and 16.17% as their share of Indian citation output respectively during 2008-17. The most productive Indian organizations were Anna University, Chennai (74 papers) and Thapar University, Patiala (48 papers) The most productive authors were I. Chana of Thapar University, Patiala (21 papers) and N. Mukherjee of Jadavpur University, Kolkata (18 papers). The 15 most productive journals contributed 43.92% share to the Indian journal publication output during 2008-17. The most productive journals were Applied Engineering Research (16 publications), Journal of Grid Computing (14 publications) and Future Generation Computer Systems (13 publications)

Task Scheduling Algorithm Research in Grid Computing

This paper studies effective task scheduling problem in the process of grid computing. Generally, task scheduling in the process of grid computing can be realized in shorter time, which guarantees the efficiency of task scheduling in grid computing. Traditional algorithm can not fully consider the resources load balance in calculating task scheduling in grid computing, resulting in network resources idleness. Finally, it can't reasonably use network resources. In order to avoid the above defects, this paper proposes a task scheduling method in grid computing based on double fitness particle swarm optimization algorithm. In the process of grid computing, channel perception method is applied to forecast the amount of grid computing tasks in the channel so as to provide the basis for task scheduling in grid computing. Realize task scheduling in grid computing by the use of double fitness particle swarm optimization algorithm. Experimental results show that under the condition of larger tasks of grid computing, the performance of task scheduling in grid computing by using the algorithm presented in this paper is superior to the traditional particle swarm optimization algorithm and can get ideal task scheduling result.

A framework for modeling and supporting data transformation services over data and knowledge grids with real‐time bound constraints

AbstractData and Knowledge Grids represent emerging and attracting application scenarios for Grid Computing, and pose novel and previously unrecognized challenges to the research community. Basically, Data and Knowledge Grids are found on high‐performance Grid infrastructures, and add to the latter meaningful data‐ and knowledge‐oriented abstractions and metaphors that perfectly marry with innovative requirements of modern complex Intelligent Information Systems. To this end, Service‐oriented Architectures and Paradigms are the most popular for Grids, and on the whole represent an active and widely recognized area of Grid Computing research. In this paper, we introduce the so‐called Grid‐based RTSOA frameworks, which essentially combine Grid Computing with real‐time service management and execution paradigms, and place emphasis for novel research perspectives in data‐intensive e‐science Grid applications on real‐time bound constraints. Grid‐based RTSOA frameworks are then specialized to the particular context of Data Transformation services over Grids, which play a relevant role for both Data and Knowledge Grids. Finally, we complete the main contribution of this paper with a rigorous theoretical model for efficiently supporting Grid‐based RTSOA frameworks, with particular emphasis on the context of Data Transformation services over Grids, along with its comprehensive experimental assessment and analysis. Copyright © 2010 John Wiley & Sons, Ltd.

Meeting security and user behavior requirements in Grid scheduling

Most of current research in Grid computing is still focused on the improvement of the performance of Grid schedulers. However, unlike traditional scheduling, in Grid systems there are other important requirements to be taken into account. One such a requirement is the secure scheduling, namely achieving an efficient allocation of tasks to reasonable trustful resources. In this paper we formalize the Grid scheduling problem as a non-cooperative non-zero sum game of the Grid users in order to address the security requirements. The premise of this model is that in a large-scale Grid, the cooperation among all users in the system is unlikely to happen. The users’ cost of playing the game is interpreted as a total cost of the secure job execution in Grid. The game cost function is minimized, at global (Grid) and local (users) levels, by using four genetic-based hybrid meta-heuristics. We have evaluated the proposed model under the heterogeneity, the large-scale and dynamics conditions using a Grid simulator. The relative performance of four hybrid schedulers is measured by the makespan and flowtime metrics. The obtained results suggested that it is more resilient for the Grid users to pay some additional scheduling cost, due to verification of the security conditions, instead of taking the risk of assigning their tasks to unreliable resources.

Grid'5000: A Large Scale And Highly Reconfigurable Experimental Grid Testbed

Large scale distributed systems such as Grids are difficult to study from theoretical models and simulators only. Most Grids deployed at large scale are production platforms that are inappropriate research tools because of their limited reconfiguration, control and monitoring capabilities. In this paper, we present Grid'5000, a 5000 CPU nation-wide infrastructure for research in Grid computing. Grid'5000 is designed to provide a scientific tool for computer scientists similar to the large-scale instruments used by physicists, astronomers, and biologists. We describe the motivations, design considerations, architecture, control, and monitoring infrastructure of this experimental platform. We present configuration examples and performance results for the reconfiguration subsystem.