Minimized Makespan Based Improved Cat Swarm Optimization for Efficient Task Scheduling in Cloud Datacenter

Abstract

Inefficient scheduling of tasks on cloud datacenter resources can result in underutilization leading to poor revenue generation. To show efficient tasks scheduling on cloud datacenter, the makespan time needs to be minimized. In this paper, we introduced a conventional Cat Swarm Optimization (CSO) task scheduling technique as an ideal solution. Although the CSO is promising in terms of convergence speed, certain improvements are required to make it efficient for cloud task scheduling since it suffers entrapment at the local search. To overcome this, we incorporated a Linear Descending Inertia Weight (LDIW) equation at the local search of the CSO technique. This led to better convergence speed and possibly ensured efficient tasks mapping on virtual resources that minimizes the makespan time. The proposed CSO-LDIW technique is implemented on CloudSim simulator tool with five (5) heterogeneous Virtual Machines (VMs) under consideration to show its performance. The results of the simulation indicate that a comparison with that of the Particle Swarm Optimization-Linear Descending Inertia Weight (PSO-LDIW) and the CSO shows that our proposed CSO-LDIW can schedule task effectively on cloud resource with a promising makespan time.