Meta-heuristic hybrid dynamic task scheduling in Heterogeneous computing environment

System State estimation and decision making are the two major components of dynamic task scheduling in a distributed computing system. Heuristic and meta-heuristic approaches seem to be the most effective methods of scheduling in Heterogeneous computing due to their ability of relative fast generation of high quality solutions. Most of the available Meta heuristic algorithms attempt to find an optimal solution with respect to a specific fixed fitness measure. The major challenges when using Genetic Algorithms to solve dynamic optimization problems are: (a) to generate and keep the diversity in the populations, which is crucial for avoiding the premature convergence to the local optima and (b) to evolve robust solutions that are able to track the optima. All of these issues will necessitate the development of intelligent adaptive algorithms that can dynamically adapt to the changes in the large-scale Computing Groups. We propose a Hybrid Genetic and Case based reasoning algorithm HGAC to improve the make span by predicting the performance of online resources to better converging the local optima and improve decision faster in dynamic environment.