Welcome guest - login - register

Nanyang Campus Grid

Projects

Projects:

  1. Grid Portal for AE@SG Digital Media

    PI:
    A/Prof. Lee Bu-Sung
    Developers:
    Tang Ming
    Zhang Junwei
    Abstract:
    The Media Grid Portal is a user's point of access to a Grid system to carry out the computing tasks for various media types. It provides an environment where the user can access Grid resources, execute and monitor Grid jobs, and collaborate with other users. The goal of our project is to allow the engineers and scientists to focus completely on their problems at hand by making the Grid a transparent extension of their desktop computing environment.

    top

  2. Grid Testbed between NTU Campus Grid and Honda RI

    Name:
    Ng Hee Khiang/Dudy/Lars/Shuja
    Supervisor:
    Dr. Ong Yew Soon, Dr. Bernhard Sendhoff
    Abstract:
    Advances in Grid Computing have recently sparkled the research and development of grid problem solving environments for complex engineering design optimization. This emerging Grid technology aims to enable collaborative computing on an unprecedented scale by leveraging compute resources, libraries, storage devices, high bandwidth network infrastructure and visualization systems that span across geographically distributed locations and organizations. The benefits of Grid computing in the context of complex engineering design and analysis are numerous. For example, in many complex engineering design problems where high-fidelity analysis models are used, each function evaluation may require a Computational Structural Mechanics (CSM), Computational Fluid Dynamics (CFD) or Computational Electro-Magnetics (CEM) simulation costing minutes to hours of supercomputer time. Since the designing process typically requires thousands of calls to the analysis model, it is often computationally prohibitive for this class of problems to locate a near optimal design. In this project, we proposed using Grid computing technologies as a powerful and inexpensive way of facilitating embarrassingly parallelism for making the designing process in science and engineering more computationally tractable.
    top

  3. Evolutionary Algorithms using the Grid Infrastructure

    Name:
    Ng Hee Khiang
    Supervisor:
    Dr. Ong Yew Soon
    Abstract:
    A scalable parallel evolutionary computing framework, which employs grid computing technologies for solving computationally expensive and intractable global optimization problems. In particular, the grid-enabled evolutionary algorithm is analyzed using an aerodynamic airfoil design optimization problem.
    top

  4. Optimization Web Services

    Name:
    Ng Hee Khiang/Wenbin
    Supervisor:
    Dr. Ong Yew Soon
    Abstract:
    Research collaboration between the School of Computer Engineering at Nanyang Technological University and the Southampton e-Science centre at the University of Southampton using a service-oriented approach for complex engineering design optimization. The service-oriented approach enables programmatic collaboration to be realized while maintaining the autonomy of individual codes at the different institutes and organizations. In the current work, a Genetic algorithm optimization logic implemented as a Grid service at Southampton is used to drive the design search process, while the aerodynamic analysis code located in Singapore is used to evaluate the objective function of the design points. Experience gathered from the current study on airfoil shape optimization is valuable for establishing effective, efficient and customised programmatic links between institutions to solve complicated engineering design problems.
    top

  5. MCCF: A Distributed Grid Job Workflow Execution Framework

    Name:
    Yuhong Feng
    Supervisor:
    Dr. Wentong Cai
    Abstract:
    With the explosion of scientific data, distributed scientific applications present great challenge to the existing execution models over the Grid. Based on the idea of having executable codes as part of Grid resources, a Mobile Code Collaboration Framework (MCCF) utilizing light-weight mobile agent and dynamic services for distributed job workflow execution is first proposed. A prototype of MCCF is implemented and performance evaluation of MCCF is carried out.

    • Gridftp: A simple code repository service is implemented as a proof-of-concept. Java byte codes will be provided at specified directory on the code repository. Gridftp is the common data transfer and access protocol which provides secure, efficient data movement over the Grid. The client uses GridFtp to download the codes. In addition, the computation result transfer is also done with Gridftp.

    • MDS: After each sub-job execution, the computational resource selection for next ready to run sub-jobs is scheduled by contacting the MDS.

    top

  6. Grid Accounting System

    Name:
    Ng Hee Khiang/Dudy Lim/Zhang JunWei
    Supervisor:
    Dr. Lee Bu Sung
    Abstract:
    Grid technology is a vision for resource owner to support their users by sharing resource. As more projects are collaborative in nature and stretch across multiple organizations, utilizing the Grid technology, it become essential for the resource owner to account for their resource usages. Thus, Grid accounting plays an important role in grid computing. In this project, we develop the prototype of Grid Accounting System towards the power grid.
    top

  7. A Framework for Constructing Temporal Relations Among Disease-Associated Genes

    Name:
    Sharon Wang
    Supervisor:
    Dr. Lee Bu Sung
    Abstract:
    The aim of this on-going project is to provide the research scientists a gobal view of upstream/downstream relations among genes of the disease of interest through text-ming of MEDLINE. The system is consisted of three components: extraction of disease-associated genes, extraction of protein-protein interactions,and construction of relations between genes.
    top

  8. The Data Grid

    Name:
    Tang Ming
    Supervisor:
    Dr. Lee Bu Sung
    Abstract:
    With the increasing number of scientific disciplines, large data collections are emerging as important community resources. Today, how to manage the huge distributed and shared data resources efficiently around the wide-area networks becomes a significant topic for both scientific research and commercial application. The Data Grid is a distributed data management and transfer architecture that provides intensive computation and analysis of shared large-scale data files, from hundreds of TeraBytes to PetaBytes, across widely distributed scientific communities. This research project of the Data Grid focuses on following areas:
    1. Data access and migration. This task handles uniform and fast transfer of files from one storage system to another.
    2. Replica management and selection. Replica management will keep track of where portions of the data set can be found. Copies of data files need to be managed in a distributed and hierarchical cache so that a set of files can be replicated to aet of remote sites and make available there. All replicas of a given file can be looked up.
    3. Query optimization. Given a query, produces a migration and replication execution plan that maximizes throughput.
    4. System performance measurement and prediction. Using the history log files and some mathematics models, find methods to measure the Data Grid performance accurately. Data Grid is essential for planning the execution of a request. The research will get a way to predict the future space availability and the time till a file will be accessed. Good predictions can also render high performances
    top

  9. Grid Resource management - A Clearinghouse

    Name:
    Percival Xavier
    Supervisor:
    Dr. Cai WenTong
    Abstract:
    Computing clusters are resources that are commonly used to execute a large variety of compute intensive applications. Examples of such applications are in areas of data mining, large-scale simulations and various optimization problems for engineering design. In research and production environments, such clusters, while are often underutilized during `trough' periods, can be in shortage during peak demand periods. Generally, enormous wastage of unused computing cycles can result from irregular usage because the full computing capacities of clusters are not utilized despite a high incidence of resource unavailability. To address this problem, a campus grid is built to allow distinct organizations that are geographically proximate to share computing clusters. The aggregation of shared resources results in a larger community-based computing infrastructure where the total cost of ownership is shared among its participants. These organizations can benefit by utilizing remote computing resources during periods of resource shortage while serving others when their resources are not in use. One such potential instantiation is a university where departments or centres are likely to be constrained by budget and floor space to install computing clusters to cope with possible shortages during peak demand periods. While sharing is an attractive solution, resource management policies must be introduced to prevent participating organizations from freeloading on each other without contributing sufficiently to the community. Such polices are administered autonomously by a resource broker called a Clearinghouse. It serves as an entry point where jobs are submitted in order to gain access the shared resources. Due to the scale of such an infrastructure, economics is employed as a means to decentralize the scheduling of jobs and regulation of equitable access to such shared resources by organizations given their respective contributions.
    top

  10. Integrating Computational Aircraft Aerodynamics Tools on The Grid

    Name:
    Hoa Nguyen
    Supervisor:
    Dr. D Murali
    Abstract:
    The project will integrate computational mesh generation and flow computation softwares; and also simulate complete aircraft aerodynamics on the campus grid.
    top

  11. Grid Testbed between NTU Campus Grid and Temasek Polytechnicv

    Name:
    Ng Hee Khiang/Dudy/Temasek Polytechnic
    Supervisor:
    N/A
    Abstract:
    To setup a Grid testbed between NTU Grid and Temasek Polytechnic
    top