Adaptive Guided Differential Evolution-based Slime Mould Algorithm-based efficient Multi-objective Task Scheduling for Cloud Computing Environments

Abstract

In a Cloud Computing (CC) environment, users are charged based on on-demand resource utilization and expected Quality of Service (QoS). Multi-Objective-based Task Scheduling (MOTS) problem formulated for achieving the expected QoS in a CC scenario is always NP-complete. The majority of existing Task Scheduling (TS) algorithms are not efficient in determining global optimal solutions due to huge space offered by large-scale problem instances and characteristics inherent in NP-complete problems. In this article, an Adaptive Guided Differential Evolution-based Slime Mould Algorithm (AGDESMA) is proposed for dealing with the problem of Multi-Objective large-scale TS optimization over Infrastructure-as-a-Service (IaaS) CC environment. The proposed AGDESMA is formulated with the merits of Slime Mould Algorithm (SMA) and Adaptive Guided Differential Evolution (AGDE) for achieving a proper balance amid exploitation and exploration phases and preventing the solutions from getting trapped into minimum local regions. It specifically adopts the method of AGDE for preventing premature convergence with maximized diversity of population and local search of swarm agents. The experimental validation of the proposed AGDESMA is conducted using CloudSim based on the synthesized and standard workload traces with larger instances up to a maximum of 5000. The results confirm the predominance of the proposed AGDESMA scheme over benchmarked schemes based on computational overhead and trade-off between makespan and financial cost.