الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 194 |  |  |
| | | from | 194 | | |
Abstract
Desktop Grid has recently been an attractive computing paradigm for high throughput applications. The most important challenges for Desktop Grid involve: 1) minimizing reliance on central servers to achieve decentralization, 2) providing interoperability with other platforms, 3) providing interaction methodologies between grid nodes that overcome connectivity problems in the Internet environment, 4) providing efficient fault tolerance to maintain performance with frequent faults, and 5) developing scheduling mechanisms that adapt to such a dynamic computing environment. This thesis proposes a novel pure P2P Desktop Grid framework in which: decentralization is completely achieved, heterogeneity problem is eliminated through providing communication between peers based on standard protocols (e.g. HTTP and FTP), implement an efficient fault-tolerance technique through application level incremental checkpointing, and provide a decentralized scheduling mechanism with matchmaking based on fuzzy logic. Experimental results show that: Using the proposed framework as a platform for running distributed applications has a great impact on improving fault tolerance, beside achieving full decentralization, Interoperability and solving connectivity problems. Implementing the proposed distributed scheduling mechanism maximized the resource utilization of the executing worker without exceeding the maximum execution time of tasks.