Implementation of Machine Learning Algorithm for Task Scheduling In Cloud Computing Environment

Abstract

For each application, efficient scheduling of heterogeneous workloads to heterogeneous processors is critical to achieving high performance. Cloud computing gives a diverse environment in which to conduct numerous tasks. In a cloud context, scheduling user requests (tasks) is an NP-hard optimization problem. To propose a sub-optimal solution to the problem, researchers present a variety of heuristic and metaheuristic strategies. In this research, we present an Ant Colony Optimization (ACO) based task scheduling (ACOTS) algorithm for lowering the average waiting time and optimising the system's makespan. In the CloudSim simulator, the designed method is implemented and simulated. Simulation results are compared to Round Robin and Random algorithms, both of which produce good results.