Transfer time-aware workflow scheduling for multi-cloud environment

Abstract

In the recent years, multi-cloud environment has attracted significant attention of the research community. Workflow scheduling in a multi-cloud environment is a challenging problem which is known to be NP-complete in nature. In this paper we propose an efficient workflow scheduling algorithm for multi-cloud environment which is based on transfer time consciousness. The proposed algorithm has two phases similar to Heterogeneous Earliest Finish time (HEFT) algorithm which was developed for multiprocessor system. The first phase calculates the B-Level priority of the tasks and second phase undergoes the virtual machines (VMs) selection based on the calculated B-level priority of the tasks. We simulate the proposed algorithm for standard scientific workflows and compare the simulated results with two existing workflow scheduling algorithms as per the proposed model. The results noticeably indicate that the proposed algorithm outperforms both the algorithms in terms of makespan and average cloud utilization.