A Genetic Based Neuro Fuzzy Technique for Process Grain Sized Scheduling of Parallel Jobs

Abstract

Problem statement: In this study, we present the development of genetic algorithm based neuro fuzzy technique for process grain sized in scheduling of parallel jobs with the help of real lIfe workload data. Approach: The study uses the rule based scheduling strategy for the scheduling and classIfies all possible scheduling strategies. The rule bases are developed with the help of the neuro fuzzy system and with the genetic fuzzy system. From the comparison of the two classIfiers of the fuzzy systems, it is found that the neuro fuzzy system results higher error rate when compared to the genetic fuzzy system. Hence the study concentrates on reducing the error rate of the results of the neuro fuzzy system by using the genetic algorithm for improving the parameters to the neuro fuzzy system. Results: The study shows that improving parameter like weights in the layers of the neuro fuzzy system using genetic algorithm reduces the error rate and comparative results of the neuro fuzzy, genetic fuzzy and the genetic based neuro fuzzy technique are shown for the parallel job scheduling. Conclusion: The study confirmed that the Genetic Based Neuro Fuzzy Technique can be used as a better optimization tool for optimizing any scheduling algorithm and this optimization tool is used in this study for agile algorithm which is used for process grain scheduling of parallel jobs.