A Reactive Fault Tolerance Approach For Cloud Computing

Reliability is a critical requirement for any system. To achieve high reliability the fault tolerance must be accomplished. Fault tolerance refers to the task must be executed even in occurring the fault. Cloud computing has emerged that grants users with access to remote computing resources. Although the current development of the cloud computing technology there are more challenges and chances of errors occur during execution. In this paper, the proposed model tolerates the faults by using replication and resubmission techniques. Then it decides which the best virtual machine depending on the reliability assessments. Then it reschedules the task once the failure occurs to the highest reliability processing node instead of replicating this task to all available nodes. Additionally, we compare our proposed model with another model that used replication and resubmission without any improvement. And we evaluate the experiments by a CloudSim simulator. We conclude that the proposed model can provide comparable performance with the traditional replication and resubmission techniques.