Network Congestion Aware Multiobjective Task Scheduling in Heterogeneous Fog Environments

Task scheduling on fog environments surges new challenges compared to scheduling on conventional cloud computing. Various levels of heterogeneity and dynamism cause task scheduling problem is more challenging for fog computing. In this study, we present a multiobjective task scheduling model with a total of five objectives and propose a multiobjective multirank (MOMRank) scheduling algorithm for fog computing. The performance of the proposed strategy is assessed with well-known multiobjective metaheuristics [the nondominated sorting genetic algorithm II (NSGA-II) and the Strength Pareto Evolutionary Algorithm 2 (SPEA2)] and a widely used algorithm from the literature, the multiobjective heterogeneous earliest finish time (MOHEFT) algorithm using three common multiobjective metrics. Additionally, we incorporate two task clustering mechanisms to the algorithms in order to improve data transmissions on interconnection networks. Results of empirical evaluations given in performance profiles over all problem instances validate significance of both our algorithm and the integrated extensions for diminishing data transfer costs.