Abstract
Recently, a newly distributed computing paradigm is established called cloud–fog paradigm by exploiting the cooperation between fog and cloud entities. In this paradigm, the main problem is task allocation which aims to select the optimal nodes among cloud and fog nodes for each task to minimize makespan, monetary and energy costs. In this paper, to solve this problem a new task allocation approach called two-tier bipartite graph with fuzzy clustering task allocation approach is proposed and it uses a hybrid DAG for representing independent and dependent tasks. In the first tier, it uses fuzzy clustering and bipartite graph to solve the uncertainty executing problem and find the maximum bipartite matching, respectively. In the second tier, it can select the best virtual machine for each assigned task inside its allocated computing node. The conducted simulation results show that the proposed approach can achieve a higher performance for makespan, total coast, and cost-makespan tradeoff than existing approaches.
•Fuzzy clustering can solve task allocation uncertainty in fog–cloud environment.•Using bipartite graph solves efficiently task allocation in fog–cloud environment.•Increasing number of cloud servers maximizes the total monetary cost of tasks.•Increasing number of fog nodes and DAG levels maximizes the makespan of tasks.