Research On Grid Workflow Scheduling Algorithm Under The Constraints Of Trust

Grid is a distributed, heterogeneous, open net environment. Resource selection and scheduling strategy is one of the key issues in grid environment. At present, only the resource node authentication is considered in many grid systems, which is insufficient to ensure the safety and reliability of the grid. Scheduling task on unreliable, disabled resources may increase task execution time and lead to rescheduling. Trust mechanism and grid scheduling mechanism are researched separately in many project, it is very few to blend trust mechanism in grid workflow task scheduling algorithm.On the basis of analyzing the current status and the key technology of grid workflow scheduling, deep research on grid workflow scheduling algorithm under the restraint of time QoS and trust QoS is done in the paper. A workflow scheduling scheme combining trust mechanism and scheduling mechanism is proposed, and also a trust computing model combining direct trust based on the task execution status and recommendation trust with recommendation factor, and a workflow scheduling algorithm based on critical tasks under the constraints of trust is designed. Firstly, backward depth of tasks is calculated in CTSA, and critical tasks are ascertained according to execution time on candidate resource. And secondly, the trust of grid resource is computed based on direct experience and recommendation experience synthetically. Lastly tasks are scheduled by decreasing backward depth and resources are closed to meet integrated function of execution time and trust and allocated for critical tasks as a priority. Resources which have minimum function combining execution time and trust are allocated to critical tasks and minimum function combining complete time and trust resource are allocated to non-critical tasks.Experiments show that, the workflow completion time is reduced and the success rate of task execution is increased by 5% to 15% and the CTSA algorithm can effectively guarantee grid scheduling resource optimization and improve the scheduling efficiency.