Evaluation of a Small Scale Cluster Computing System for Parallel Intelligent Techniques Applications

A small scale distributed computing system that is able to meet the needs of parallel intelligent techniques for engineering and science applications is reported in this paper. The reported system is a cluster of general-purpose PCs interconnected in a network. Such systems are powerful yet low cost. While such systems are not new, most applications written for cluster systems are programmed in MPI-C. Results from the proposed system have shown that it is advantageous to use Java due to its simplicity and mobility. Hence, the goal of this research is to design a Java-based parallel platform for efficient execution of intelligent techniques for engineering and science applications on a cluster system.