Cloud computing in the field of high-performance distributed computing has emerged as a new development in which the demand for access to resources via the Internet is presented in distributed servers that dynamically scale Are acceptable. One of the important research issues that must be considered to achieve efficient performance is fault tolerance. Fault tolerance is a way to find faults and failures in a system. Predicting and reducing errors play an important role in increasing the performance and popularity of cloud computing. In this study, an adaptive workflow scheduling approach is presented to increase fault tolerance in cloud computing. The present approach calculates the probability of failure for each resource according to the execution time of tasks on the resources. In the present method, a deadline is set for each of the tasks. If the task is not completed within the specified time, the probability of failure in the source increases and subsequent tasks are not sent to the desired source. The simulation results of the proposed method show that the proposed idea can work well on workflows and improve service quality factors.
Read full abstract