Title :
Research and Implementation Issues of Fusegrid
Author :
Qi, De-yu ; Lin, Wei-wei
Author_Institution :
Sch. of Comput. Eng. & Sci., South China Univ. of Tech., Guangzhou Guangdong
Abstract :
After analyzing problems in current grid environments, a new grid architecture (called FuseGrid) based on the tree-shaped fusion of resources is presented in this paper. JVMs act as a base computing resources in the proposed grid architecture, in which all objects that can be accessed by computer systems are regarded as resources and they are aggregated and fused in the form of tree from bottom to top, forming new resources of higher level. After introducing an overview of FuseGrid and discussing its functionality model, the key issues of FuseGrid implementation, the algorithms for tree building, dynamic reconfiguring tree and resource searching are presented in this paper. Then, it focuses on the task allocation algorithm using dynamic load balancing for large-scale applications in FuseGrid. Finally, the experiments show that FuseGrid has excellent performance when it is used as an execution environment of large batch of Java applications
Keywords :
Java; grid computing; resource allocation; tree data structures; FuseGrid implementation; JVM; computer system; dynamic load balancing; dynamic reconfiguring tree; grid environment; large-scale application; resource searching; tree-shaped fusion; Computer architecture; Concurrent computing; Cybernetics; Distributed computing; Grid computing; Java; Large-scale systems; Machine learning; Parallel processing; Parallel programming; Protocols; Resource management; Grid; jvm; tree; virtual resource;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258829