A novel energy-based task scheduling in fog computing environment: an improved artificial rabbits optimization approach

Fog computing utilizes user premises resources to provide better services than traditional cloud computing. Due to the heterogeneity of fog devices, scheduling poses a challenge. This paper proposes a novel version of artificial rabbits optimization (ARO) called the Nonlinear based chaotic artificial rabbits optimization (NCARO) and utilizes NCARO for task scheduling in the fog computing environment (TSNCARO). The NCARO optimizes ARO by using chaotic and nonlinear control parameters. In the proposed method, chaotic maps are used to improve the exploratory behavior of ARO. ARO’s exploratory and exploitative behaviors are also adjusted by means of a nonlinear control parameter. Three objectives are considered: service time, cost, and energy consumption. It improves performance by prioritizing tasks according to deadlines. An extensive scenario compares NCARO and TSNCARO algorithms with other algorithms. On the basis of the comparison results, the proposed algorithms achieved the best results in terms of makespan, service time, total cost, energy consumption, carbon dioxide emission rate, and percentage of deadline satisfaction.