An Adaptive Grid Workflow Scheduling Based on Bottleneck Detection and Execution Context

Scheduling of Grid workflows has been a prevalent research area as it is the mechanism that helps improving the efficiency of the Grid workflow execution. The most common goal of scheduling workflow in the Grid is to minimize execution makespan and many algorithms have been proposed to address this issue. However, most of the algorithms so far usually focus and are implemented based on a single principle and act according to that principle. Only few algorithms consider adaptive scheduling process that acts differently in different situations. In this paper, we propose an adaptive Grid workflow scheduling that reacts to the presence of bottlenecks and different execution context. With this adaptive approach, the proposed algorithm can achieve better overall makespan. Simulations of parameter sweep workflows with single instance and multiple instances executed in parallel are used to evaluate the algorithm against four existing algorithms.