Spider monkey optimization based resource allocation and scheduling in fog computing environment

Abstract

Spider monkey optimization (SMO) is a quite popular and recent swarm intelligence algorithm for numerical optimization. SMO is Fission-Fusion social structure based algorithm inspired by spider monkey’s behavior. The algorithm proves to be very efficient in solving various constrained and unconstrained optimization problems. This paper presents the application of SMO in fog computing. We propose a heuristic initialization based spider monkey optimization algorithm for resource allocation and scheduling in a fog computing network. The algorithm minimizes the total cost (service time and monetary cost) of tasks by choosing the optimal fog nodes. Longest job fastest processor (LJFP), shortest job fastest processor (SJFP), and minimum completion time (MCT) based initialization of SMO are proposed and compared with each other. The performance is compared based on the parameters of average cost, average service time, average monetary cost, and the average cost per schedule. The results demonstrate the efficacy of MCT-SMO as compared to other heuristic initialization based SMO algorithms and Particle Swarm Optimization (PSO).

Keywords

• Swarm intelligence
• Spider monkey optimization
• Fog computing
• Task scheduling