Task Partitioning Scheduling Algorithms for Heterogeneous Multi-Cloud Environment

Cloud computing is now an emerging trend for cost-effective, universal access, reliability, availability, recovery and flexible IT resources. Although cloud computing has a tremendous growth, there is a wide scope of research in different dimensions. For instance, one of the challenging topics is task scheduling problem, which is shown to be NP-Hard. Recent studies report that the tasks are assigned to clouds based on their current load, without considering the partition of a task into pre-processing and processing time. Here, pre-processing time is the time needed for initialization, linking and loading of a task, whereas processing time is the time needed for the execution of a task. In this paper, we present three task partitioning scheduling algorithms, namely cloud task partitioning scheduling (CTPS), cloud min–min task partitioning scheduling and cloud max–min task partitioning scheduling, for heterogeneous multi-cloud environment. The proposed CTPS is an online scheduling algorithm, whereas others are offline scheduling algorithm. Basically, these proposed algorithms partition the tasks into two different phases, pre-processing and processing, to schedule a task in two different clouds. We compare the proposed algorithms with four task scheduling algorithms as per their applicability. All the algorithms are extensively simulated and compared using various benchmark and synthetic datasets. The simulation results show the benefit of the proposed algorithms in terms of two performance metrics, makespan and average cloud resource utilization. Moreover, we evaluate the simulation results using analysis of variance statistical test and confidence interval.